Daily Papers

Leveraging Multimodal Large Language Models (MLLMs) has become pivotal for advancing Universal Multimodal Embeddings (UME) in addressing diverse cross-modal tasks. Recent studies demonstrate that incorporating generative Chain-of-Thought (CoT) reasoning can substantially enhance task-specific representations compared to discriminative methods. However, the generated reasoning CoTs of existing generative embedding methods are limited to the textual analysis of queries and are irrelevant to the retrieval of the targets. To address these limitations, we propose a reasoning-driven UME framework that integrates Embedder-Guided Reinforcement Learning (EG-RL) to optimize the Reasoner to produce evidential Traceability CoT (T-CoT). Our key contributions are threefold: (1) We design an EG-RL framework where the Embedder provides explicit supervision to the Reasoner, ensuring the generated CoT traces are aligned with embedding tasks. (2) We introduce T-CoT, which extracts critical multimodal cues to focus on retrieval-relevant elements and provides multimodal inputs for the Embedder. (3) With limited computational resources, our framework outperforms the pioneering embedding model on both MMEB-V2 and UVRB benchmarks. The integration of multimodal evidence in structured reasoning, paired with retrieval-oriented alignment, effectively strengthens cross-modal semantic consistency and boosts the fine-grained matching capability of the model as well as the generalization across complex scenarios. Our work demonstrates that targeted reasoning optimization can significantly improve multimodal embedding quality, providing a practical and efficient solution for reasoning-driven UME development.

Requirement traceability is the process of identifying the inter-dependencies between requirements. It poses a significant challenge when conducted manually, especially when dealing with requirements at various levels of abstraction. In this work, we propose a novel approach to automate the task of linking high-level business requirements with more technical system requirements. The proposed approach begins by representing each requirement using a Bag of-Words (BOW) model combined with the Term Frequency-Inverse Document Frequency (TF-IDF) scoring function. Then, we suggested an enhanced cosine similarity that uses recent advances in word embedding representation to correct traditional cosine similarity function limitations. To evaluate the effectiveness of our approach, we conducted experiments on three well-known datasets: COEST, WARC(NFR), and WARC(FRS). The results demonstrate that our approach significantly improves efficiency compared to existing methods. We achieved better results with an increase of approximately 18.4% in one of the datasets, as measured by the F2 score.

Software requirements traceability is a critical component of the software engineering process, enabling activities such as requirements validation, compliance verification, and safety assurance. However, the cost and effort of manually creating a complete set of trace links across natural language artifacts such as requirements, design, and test-cases can be prohibitively expensive. Researchers have therefore proposed automated link-generation solutions primarily based on information-retrieval (IR) techniques; however, these solutions have failed to deliver the accuracy needed for full adoption in industrial projects. Improvements can be achieved using deep-learning traceability models; however, their efficacy is impeded by the limited size and availability of project-level artifacts and links to serve as training data. In this paper, we address this problem by proposing and evaluating several deep-learning approaches for text-to-text traceability. Our method, named NLTrace, explores three transfer learning strategies that use datasets mined from open world platforms. Through pretraining Language Models (LMs) and leveraging adjacent tracing tasks, we demonstrate that NLTrace can significantly improve the performance of LM based trace models when training links are available. In such scenarios NLTrace outperforms the best performing classical IR method with an 188% improvement in F2 score and 94.01% in Mean Average Precision (MAP). It also outperforms the general LM based trace model by 7% and 23% for F2 and MAP respectively. In addition, NLTrace can adapt to low-resource tracing scenarios where other LM models can not. The knowledge learned from adjacent tasks enables NLTrace to outperform VSM models by 28% F2 on generation challenges when presented with a small number of training examples.

The ModelWriter platform provides a generic framework for automated traceability analysis. In this paper, we demonstrate how this framework can be used to trace the consistency and completeness of technical documents that consist of a set of System Installation Design Principles used by Airbus to ensure the correctness of aircraft system installation. We show in particular, how the platform allows the integration of two types of reasoning: reasoning about the meaning of text using semantic parsing and description logic theorem proving; and reasoning about document structure using first-order relational logic and finite model finding for traceability analysis.

Chain-of-thought (CoT) outputs let us read a model's step-by-step reasoning. Since any long, serial reasoning process must pass through this textual trace, the quality of the CoT is a direct window into what the model is thinking. This visibility could help us spot unsafe or misaligned behavior (monitorability), but only if the CoT is transparent about its internal reasoning (faithfulness). Fully measuring faithfulness is difficult, so researchers often focus on examining the CoT in cases where the model changes its answer after adding a cue to the input. This proxy finds some instances of unfaithfulness but loses information when the model maintains its answer, and does not investigate aspects of reasoning not tied to the cue. We extend these results to a more holistic sense of monitorability by introducing verbosity: whether the CoT lists every factor needed to solve the task. We combine faithfulness and verbosity into a single monitorability score that shows how well the CoT serves as the model's external `working memory', a property that many safety schemes based on CoT monitoring depend on. We evaluate instruction-tuned and reasoning models on BBH, GPQA, and MMLU. Our results show that models can appear faithful yet remain hard to monitor when they leave out key factors, and that monitorability differs sharply across model families. We release our evaluation code using the Inspect library to support reproducible future work.

Software traceability establishes and leverages associations between diverse development artifacts. Researchers have proposed the use of deep learning trace models to link natural language artifacts, such as requirements and issue descriptions, to source code; however, their effectiveness has been restricted by availability of labeled data and efficiency at runtime. In this study, we propose a novel framework called Trace BERT (T-BERT) to generate trace links between source code and natural language artifacts. To address data sparsity, we leverage a three-step training strategy to enable trace models to transfer knowledge from a closely related Software Engineering challenge, which has a rich dataset, to produce trace links with much higher accuracy than has previously been achieved. We then apply the T-BERT framework to recover links between issues and commits in Open Source Projects. We comparatively evaluated accuracy and efficiency of three BERT architectures. Results show that a Single-BERT architecture generated the most accurate links, while a Siamese-BERT architecture produced comparable results with significantly less execution time. Furthermore, by learning and transferring knowledge, all three models in the framework outperform classical IR trace models. On the three evaluated real-word OSS projects, the best T-BERT stably outperformed the VSM model with average improvements of 60.31% measured using Mean Average Precision (MAP). RNN severely underperformed on these projects due to insufficient training data, while T-BERT overcame this problem by using pretrained language models and transfer learning.

Establishing precise traceability between embedded systems datasheets and their corresponding code implementations remains a fundamental challenge in systems engineering, particularly for low-level software where manual mapping between specification documents and large code repositories is infeasible. Existing Traceability Link Recovery approaches primarily rely on lexical similarity and information retrieval techniques, which struggle to capture the semantic, structural, and symbol level relationships prevalent in embedded systems software. We present a hierarchical datasheet-to-code mapping methodology that employs large language models for semantic analysis while explicitly structuring the traceability process across multiple abstraction levels. Rather than performing direct specification-to-code matching, the proposed approach progressively narrows the search space through repository-level structure inference, file-level relevance estimation, and fine-grained symbollevel alignment. The method extends beyond function-centric mapping by explicitly covering macros, structs, constants, configuration parameters, and register definitions commonly found in systems-level C/C++ codebases. We evaluate the approach on multiple open-source embedded systems repositories using manually curated datasheet-to-code ground truth. Experimental results show substantial improvements over traditional information-retrieval-based baselines, achieving up to 73.3% file mapping accuracy. We significantly reduce computational overhead, lowering total LLM token consumption by 84% and end-to-end runtime by approximately 80%. This methodology supports automated analysis of large embedded software systems and enables downstream applications such as training data generation for systems-aware machine learning models, standards compliance verification, and large-scale specification coverage analysis.

Chain-of-thought (CoT) monitoring is increasingly treated as an important safety layer for frontier reasoning models. Most monitorability evaluations study explicit-influence settings: setups where the prompt directly incentivizes the model to hide something, e.g., by instructing it to perform a hidden side-task. A complementary axis for CoT-monitor evaluations is implicit-influence settings, where the prompt contains no instruction to hide, but the model's behavior is still shaped by features of the task or context, e.g. an irrelevant detail about a candidate that biases a hiring rating. We introduce the first benchmark that directly compares CoT monitorability under the two regimes. We test how model behavior changes in the presence of a nudge to choose a particular option. The nudge is delivered either as a casual aside (implicit), or as a direct instruction to act on the nudge and to conceal having done so (explicit). The benchmark spans four task formats (binary choice, numeric rating, multiple-choice QA, open-ended coding) and seven frontier extended-thinking models. Under explicit influence, a CoT monitor detects 60-94% of behavior shifts: even models instructed to conceal it leak the instruction into their CoT. Under implicit influence, the same factors still shift behavior, but detection falls by 41-46 percentage points in two of our four settings. Realistic system-prompt additions (of the kind a developer might deploy to reduce off-topic bias) lower implicit detection further, to as low as 5%, while preserving the behavioral influence itself. These results suggest that monitorability estimates obtained in explicit-influence settings may over-estimate monitorability, and that monitorability can be further decreased by well-intentioned deployment choices. Our benchmark and code are available at https://github.com/agatha-duzan/implicit-vs-explicit-influence

Large language models (LLMs) can generate chains of thought (CoTs) that are not always causally responsible for their final outputs. When such a mismatch occurs, the CoT no longer faithfully reflects the decision-critical factors driving the model's behavior, leading to the reduced CoT monitorability problem. However, a comprehensive and fully open-source benchmark for studying CoT monitorability remains lacking. To address this gap, we propose MonitorBench, a systematic benchmark for evaluating CoT monitorability in LLMs. MonitorBench provides: (1) a diverse set of 1,514 test instances with carefully designed decision-critical factors across 19 tasks spanning 7 categories to characterize when CoTs can be used to monitor the factors driving LLM behavior; and (2) two stress-test settings to quantify the extent to which CoT monitorability can be degraded. Extensive experiments across multiple popular LLMs with varying capabilities show that CoT monitorability is higher when producing the final target response requires structural reasoning through the decision-critical factor. Closed-source LLMs generally show lower monitorability, and there exists a negative relationship between monitorability and model capability. Moreover, both open- and closed-source LLMs can intentionally reduce monitorability under stress-tests, with monitorability dropping by up to 30% in some tasks that do not require structural reasoning over the decision-critical factors. Beyond these empirical insights, MonitorBench provides a basis for further research on evaluating future LLMs, studying advanced stress-test monitorability techniques, and developing new monitoring approaches.

Chain-of-thought (CoT) monitoring is a promising tool for detecting misbehaviors and understanding the motivations of modern reasoning models. However, if models can control what they verbalize in their CoT, it could undermine CoT monitorability. To measure this undesirable capability -- CoT controllability -- we introduce the CoT-Control evaluation suite, which includes tasks that require models to solve problems while adhering to CoT instructions, e.g., reasoning about a genetics question without using the word 'chromosome'. We show that reasoning models possess significantly lower CoT controllability than output controllability; for instance, Claude Sonnet 4.5 can control its CoT only 2.7% of the time but 61.9% when controlling its final output. We also find that CoT controllability is higher for larger models and decreases with more RL training, test-time compute, and increased problem difficulty. CoT controllability failures extend even to situations in which models are given incentives (as opposed to direct requests) to evade CoT monitors, although models exhibit slightly higher controllability when they are told they are being monitored. Similarly, eliciting controllability by adversarially optimizing prompts does not meaningfully increase controllability. Our results leave us cautiously optimistic that CoT controllability is currently unlikely to be a failure mode of CoT monitorability. However, the mechanism behind low controllability is not well understood. Given its importance for maintaining CoT monitorability, we recommend that frontier labs track CoT controllability in future models.

Image Chain-of-Thought (Image-CoT) is a test-time scaling paradigm that improves image generation by extending inference time. Most Image-CoT methods focus on text-to-image (T2I) generation. Unlike T2I generation, image editing is goal-directed: the solution space is constrained by the source image and instruction. This mismatch causes three challenges when applying Image-CoT to editing: inefficient resource allocation with fixed sampling budgets, unreliable early-stage verification using general MLLM scores, and redundant edited results from large-scale sampling. To address this, we propose ADaptive Edit-CoT (ADE-CoT), an on-demand test-time scaling framework to enhance editing efficiency and performance. It incorporates three key strategies: (1) a difficulty-aware resource allocation that assigns dynamic budgets based on estimated edit difficulty; (2) edit-specific verification in early pruning that uses region localization and caption consistency to select promising candidates; and (3) depth-first opportunistic stopping, guided by an instance-specific verifier, that terminates when intent-aligned results are found. Extensive experiments on three SOTA editing models (Step1X-Edit, BAGEL, FLUX.1 Kontext) across three benchmarks show that ADE-CoT achieves superior performance-efficiency trade-offs. With comparable sampling budgets, ADE-CoT obtains better performance with more than 2x speedup over Best-of-N.

Chain-of-thought (CoT) reasoning has advanced medical visual question answering (VQA), yet most existing CoT rationales are free-form and fail to capture the structured reasoning process clinicians actually follow. This work asks: Can traceable, multi-step reasoning supervision improve reasoning accuracy and the interpretability of Medical VQA? To this end, we introduce Step-CoT, a large-scale medical reasoning dataset with expert-curated, structured multi-step CoT aligned to clinical diagnostic workflows, implicitly grounding the model's reasoning in radiographic evidence. Step-CoT comprises more than 10K real clinical cases and 70K VQA pairs organized around diagnostic workflows, providing supervised intermediate steps that guide models to follow valid reasoning trajectories. To effectively learn from Step-CoT, we further introduce a teacher-student framework with a dynamic graph-structured focusing mechanism that prioritizes diagnostically informative steps while filtering out less relevant contexts. Our experiments show that using Step-CoT can improve reasoning accuracy and interpretability. Benchmark: github.com/hahaha111111/Step-CoT. Dataset Card: huggingface.co/datasets/fl-15o/Step-CoT

Code generation is to automatically generate source code conforming to a given programming specification, which has received extensive attention especially with the development of large language models (LLMs). Due to the inherent difficulty of code generation, the code generated by LLMs may be also not aligned with the specification. To improve the perfor mance of LLMs in code generation, some Chain of Thought (CoT) techniques have been proposed to guide LLMs for programming understanding before code generation. However, they are still hard to figure out complicated programming logic according to the (concise) specification, leadingto unsatisfactory code generation performance. In this work, we propose the first test-case-driven CoT technique, called TCoT, to further enhance the ability of LLMs in code generation. It understands the programming specification from the novel perspective of test cases, which is aligned with human practice by using examples to understand complicated problems. Due to the existence of the expected output specified in a test case, TCoT can instantly check the correctness of the programming understanding and then refine it to be as correct as possible before code generation. In this way, it is more likely to generate correct code. Our evaluation on 6 datasets and 14 baselines demonstrates the effectiveness of TCoT. For example, TCoT improves ChatGPT by 13.93%~69.44% in terms of Pass@1 (measuring the ratio of programming problems for which the generated code passes all test cases), and outperforms the existing CoT technique with the improvement of 12.14%~53.72% in terms of Pass@1.

Large reasoning models (LRMs) spend substantial test-time compute on long chain-of-thought (CoT) traces, but what *characterizes* an effective CoT remains unclear. While prior work reports gains from lengthening CoTs and increasing review (revisiting earlier steps) via appended *wait* tokens, recent studies suggest that shorter thinking can outperform longer traces. We therefore conduct a systematic evaluation across ten LRMs on math and scientific reasoning. Contrary to the "longer-is-better" narrative, we find that both naive CoT lengthening and increased review are associated with *lower* accuracy. As CoT unfolds step by step, token-level metrics can conflate verbosity with process quality. We introduce a graph view of CoT to extract structure and identify a single statistic-the *Failed-Step Fraction (FSF)*, the fraction of steps in abandoned branches-that consistently outpredicts length and review ratio for correctness across models. To probe causality, we design two interventions. First, we rank candidate CoTs by each metric at test time, where FSF yields the largest pass@1 gains; second, we edit CoTs to remove failed branches, which significantly improves accuracy, indicating that failed branches bias subsequent reasoning. Taken together, these results characterize effective CoTs as those that *fail less* and support *structure-aware* test-time scaling over indiscriminately generating long CoT.

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows some misbehavior to go unnoticed. Nevertheless, it shows promise and we recommend further research into CoT monitorability and investment in CoT monitoring alongside existing safety methods. Because CoT monitorability may be fragile, we recommend that frontier model developers consider the impact of development decisions on CoT monitorability.

Chain-of-thought (CoT) reasoning has been proposed as a transparency mechanism for large language models in safety-critical deployments, yet its effectiveness depends on faithfulness (whether models accurately verbalize the factors that actually influence their outputs), a property that prior evaluations have examined in only two proprietary models, finding acknowledgment rates as low as 25% for Claude 3.7 Sonnet and 39% for DeepSeek-R1. To extend this evaluation across the open-weight ecosystem, this study tests 12 open-weight reasoning models spanning 9 architectural families (7B-685B parameters) on 498 multiple-choice questions from MMLU and GPQA Diamond, injecting six categories of reasoning hints (sycophancy, consistency, visual pattern, metadata, grader hacking, and unethical information) and measuring the rate at which models acknowledge hint influence in their CoT when hints successfully alter answers. Across 41,832 inference runs, overall faithfulness rates range from 39.7% (Seed-1.6-Flash) to 89.9% (DeepSeek-V3.2-Speciale) across model families, with consistency hints (35.5%) and sycophancy hints (53.9%) exhibiting the lowest acknowledgment rates. Training methodology and model family predict faithfulness more strongly than parameter count, and keyword-based analysis reveals a striking gap between thinking-token acknowledgment (approximately 87.5%) and answer-text acknowledgment (approximately 28.6%), suggesting that models internally recognize hint influence but systematically suppress this acknowledgment in their outputs. These findings carry direct implications for the viability of CoT monitoring as a safety mechanism and suggest that faithfulness is not a fixed property of reasoning models but varies systematically with architecture, training method, and the nature of the influencing cue.

Semantic-ID mappings are reusable interfaces between item tokenizers and generative recommenders, yet released mappings rarely state whether they are coherent, what structure they expose, how generated paths resolve, or what must be revalidated after a refresh. SIDScope is a source-traced diagnostic resource for these decisions. It normalizes item-to-code artifacts, verifies provenance and joins, profiles mapping structure, compares paired revisions, and accounts for path-to-item outcomes in generated traces. Across nine source-traced tokenizer exports from seven families on Amazon and Yelp data - eight executable routes plus one auditable snapshot - SIDScope reveals that interface health is multi-signal rather than scalar. Its central finding is mechanism-conditional: prefix alignment strongly tracks held-out candidate exposure when retrieval consumes SID prefixes, then weakens as scoring becomes prefix-independent. Trained trace accounting exposes a second hidden gap: a valid target path can survive without uniquely retrieving the target item by 1.2-3.0 percentage points. A refresh case establishes a third: repairing the mapping does not by itself restore an inherited generator; model reuse requires a separate handoff check. The package provides frozen evidence summaries, conformance reports, trace labels, table builders, and CPU-only verifiers. It supports decisions about artifact readiness, interface risks, and revalidation before model reuse.

Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models by encouraging step-by-step intermediate reasoning, and recent advances have extended this paradigm to Multimodal Large Language Models (MLLMs). In the medical domain, where diagnostic decisions depend on nuanced visual cues and sequential reasoning, CoT aligns naturally with clinical thinking processes. However, Current benchmarks for medical image understanding generally focus on the final answer while ignoring the reasoning path. An opaque process lacks reliable bases for judgment, making it difficult to assist doctors in diagnosis. To address this gap, we introduce a new M3CoTBench benchmark specifically designed to evaluate the correctness, efficiency, impact, and consistency of CoT reasoning in medical image understanding. M3CoTBench features 1) a diverse, multi-level difficulty dataset covering 24 examination types, 2) 13 varying-difficulty tasks, 3) a suite of CoT-specific evaluation metrics (correctness, efficiency, impact, and consistency) tailored to clinical reasoning, and 4) a performance analysis of multiple MLLMs. M3CoTBench systematically evaluates CoT reasoning across diverse medical imaging tasks, revealing current limitations of MLLMs in generating reliable and clinically interpretable reasoning, and aims to foster the development of transparent, trustworthy, and diagnostically accurate AI systems for healthcare. Project page at https://juntaojianggavin.github.io/projects/M3CoTBench/.

Despite significant advancements in the general capability of large language models (LLMs), they continue to struggle with consistent and accurate reasoning, especially in complex tasks such as mathematical and code reasoning. One key limitation is that LLMs are trained primarily on correct solutions, reducing their ability to detect and learn from errors, which hampers their ability to reliably verify and rank outputs. To address this, we scale up the inference-time computation by generating multiple reasoning paths and employing verifiers to assess and rank the generated outputs by correctness. To facilitate this, we introduce a comprehensive dataset consisting of correct and incorrect solutions for math and code tasks, generated by multiple LLMs. This diverse set of solutions enables verifiers to more effectively distinguish and rank correct answers from erroneous outputs. The training methods for building verifiers were selected based on an extensive comparison of existing approaches. Moreover, to leverage the unique strengths of different reasoning strategies, we propose a novel collaborative method integrating Chain-of-Thought (CoT) and Program-of-Thought (PoT) solutions for verification. CoT provides a clear, step-by-step reasoning process that enhances interpretability, while PoT, being executable, offers a precise and error-sensitive validation mechanism. By taking both of their strengths, our approach significantly improves the accuracy and reliability of reasoning verification. Our verifiers, Math-Rev and Code-Rev, demonstrate substantial performance gains to existing LLMs, achieving state-of-the-art results on benchmarks such as GSM8k and MATH and even outperforming GPT-4o with Qwen-72B-Instruct as the reasoner.

Current coding-agent benchmarks usually pro- vide the full task specification upfront. Real research coding often does not: the intended system is progressively disclosed through in- teraction, requiring the agent to track durable design commitments across a long session. We introduce a benchmark for this setting and study faithfulne Ss Loss U nder eM ergent s Pecification (SLUMP), defined as the reduc- tion in final implementation faithfulness un- der emergent specification relative to a single- shot specification control. The benchmark con- tains 20 recent ML papers (10 ICML 2025, 10 NeurIPS 2025), 371 atomic verifiable compo- nents, and interaction scripts of approximately 60 coding requests that progressively disclose the target design without revealing the paper itself. Final repositories are scored with a five-level component-faithfulness rubric and accompanied by an exposure audit to verify that scored components are recoverable from the visible interaction. Evaluated on Claude Code and Codex, the single-shot specification control achieves higher overall implementation fidelity on 16/20 and 14/20 papers, respectively. Structural integration degrades under emergent specification on both platforms, while seman- tic faithfulness loss is substantial on Claude Code and small on Codex. As a mitigation case study, we introduce ProjectGuard, an exter- nal project-state layer for specification tracking. On Claude Code, ProjectGuard recovers 90% of the faithfulness gap, increases fully faith- ful components from 118 to 181, and reduces severe failures from 72 to 49. These results identify specification tracking as a distinct eval- uation target for long-horizon coding agents.

Chain-of-thought (CoT) monitoring has been proposed as a promising safety mechanism for detecting misaligned behavior in large language models. However, its reliability remains largely unexplored beyond English and across diverse model families. We present the first large-scale evaluation of CoT monitorability across 13 diverse languages and seven frontier model families, comprising 16 models. Using adversarial-hint evaluations that require explicit intermediate computation, together with analysis of internal answer-token probabilities, we consistently find CoT unfaithfulness across languages and hint types, with an average rate of 95.9\% across 8B--120B parameter models. We find that frontier models systematically engage in strategic manipulation, including answer-switching, post-hoc rationalization, and procedural exploitation of hints, making external monitors struggle to detect deception. We show that frontier models often commit to the misaligned cue in their latent activations within the first 15\% of generation, even when the CoT appears faithful. Surprisingly, these deceptive patterns remain 100\% in low-resource languages, revealing fundamental limitations in current CoT-based oversight. Our results reveal that CoT monitoring is fundamentally fragile under linguistic distribution shift, providing a substantially weaker safety signal than what English-only studies suggest. These findings underscore an urgent need to develop robust CoT monitors and to accelerate research into white-box monitoring techniques, especially to improve CoT monitorability in mid- and low-resource languages. Our code is available https://multilingual-cot-monitoring.github.io/{blue{here}}.

Monitoring chain-of-thought (CoT) reasoning is a foundational safety technique for large language model (LLM) agents; however, this oversight is compromised if models learn to conceal their reasoning. We explore the potential for steganographic CoT -- where models hide secret reasoning within innocuous text -- to inform risk assessment and deployment policies. We systematically evaluate the limits of steganographic capabilities across 28 models, ranging from past generations to the current frontier. We measure monitor evasion, refusal rates, encoding fidelity, and hidden task accuracy across four datasets, comparing steganographic acrostics against plain reasoning and filler-token baselines. We find that current models cannot yet sustain hidden reasoning for complex math and arithmetic tasks. However, in a simplified counting experiment, Claude Opus 4.5 achieved 92% accuracy on the hidden task, demonstrating nascent capability. Notably, in rare cases (<1%), GPT-5.2 might refuse steganographic instructions while simultaneously complying with them. Our findings underscore the need for continuous evaluation of steganographic risks. This study provides a methodology to preemptively detect and prevent hidden reasoning that might empower misaligned scheming and deceptive behavior.

Enterprise large language model (LLM) applications often begin as prototypes whose behavior is carried by prompts and retrieval context. Productization adds requirements for source boundaries, entity routing, answer contracts, and reproducible traces. We present a harness-engineering approach that reconstructs this pattern into a traceable, auditable LLM-agent architecture: deterministic behavior moves into code, manifests, schemas, and validation artifacts around a replaceable composition boundary, while source-backed claims remain the authority for runtime answers. We instantiate it on a public-data slice of five Korean corporate groups (25 listed companies) and evaluate three research questions. (1) The harness preserves its source-grounding, entity-routing, trace, output-hygiene, and recommendation-language contracts across the fixed validation scenarios; a fault-injection control confirms the validators flag deliberately broken contracts. (2) The checks the harness enforces held under model substitution: across three hosted models, they passed on all 270 composition-boundary runs; failures were confined to the model-composed side and were caught and recorded. (3) The code-owned guarantees are load-bearing, not reproducible by prompting alone: holding the model fixed and varying only the enforcement layer, prompt instructions alone let recommendation-language and internal-trace-leakage violations reach the reader, which the harness blocks entirely. A bolt-on external guardrail prevents such violations too but over-refuses, dropping utility to 88/120 where the harness preserves full utility (120/120); in this ablation, only code-owned enforcement preserves both safety and utility. The result is a reusable engineering pattern for turning exploratory prototypes into auditable applications with versioned source, control, and validation artifacts.

Learning complex functions that involve multi-step reasoning poses a significant challenge for standard supervised learning from input-output examples. Chain-of-thought (CoT) supervision, which provides intermediate reasoning steps together with the final output, has emerged as a powerful empirical technique, underpinning much of the recent progress in the reasoning capabilities of large language models. This paper develops a statistical theory of learning under CoT supervision. A key characteristic of the CoT setting, in contrast to standard supervision, is the mismatch between the training objective (CoT risk) and the test objective (end-to-end risk). A central part of our analysis, distinguished from prior work, is explicitly linking those two types of risk to achieve sharper sample complexity bounds. This is achieved via the *CoT information measure* I_{D, h_star}^{CoT}(epsilon; calH), which quantifies the additional discriminative power gained from observing the reasoning process. The main theoretical results demonstrate how CoT supervision can yield significantly faster learning rates compared to standard E2E supervision. Specifically, it is shown that the sample complexity required to achieve a target E2E error epsilon scales as d/I_{D, h_star}^{CoT}(epsilon; calH), where d is a measure of hypothesis class complexity, which can be much faster than standard d/epsilon rates. Information-theoretic lower bounds in terms of the CoT information are also obtained. Together, these results suggest that CoT information is a fundamental measure of statistical complexity for learning under chain-of-thought supervision.

Applied Behavior Analysis (ABA) is a clinical discipline whose documentation, teaching programs and multi-session behavioral logs, is formulaic and high-volume, yet real session data is HIPAA-protected and bound by professional confidentiality rules, blocking the release of a training corpus. We present TRACE (Taxonomy-Referenced ABA Clinical Examples), a 2,999-example synthetic instruction-tuning dataset covering two ABA tasks: teaching-program generation across Discrete Trial Training, Natural Environment Teaching, and Task Analysis; and multi-session behavioral interpretation across twelve trajectory patterns and thirteen target behaviors. Every example is produced by a deterministic taxonomy-driven generator grounded in the canonical ABA literature, and every example carries complete sampling provenance, the exact taxonomy cells that produced it. The dataset is released under CC BY-NC 4.0 for data and MIT for code, with stratified train (2,549), validation (149), test (281), and sanity (20) splits. TRACE is a research artifact and has not been clinically validated.

Chains of thought (CoTs) have become central in interpreting and auditing behaviors of large language models. Yet growing evidence suggests that these traces often fail to faithfully represent the computations behind a model's predictions. Several faithfulness metrics have been proposed, but whether they indeed measure faithfulness remains unknown. Answering this requires ground-truth labels, which are hard to obtain since internal computations are not directly observable. Consequently, most works proposing metrics report only absolute scores or comparisons to prior metrics, and the few existing benchmarks rely on proxies like plausibility or importance, properties orthogonal to faithfulness that can mislead about whether a CoT can be trusted. We address this challenge by constructing tasks whose outputs reveal which intermediate computations must have produced them, and developing an automated labeling pipeline that yields ground-truth faithfulness labels at both the step and CoT level. Building on this methodology, we present BonaFide, a benchmark of 3,066 labeled CoTs across 13 tasks and 10 models, and use it to conduct the first systematic evaluation of prominent faithfulness metrics. Our experiments show that most metrics perform near chance, exhibit strong prediction biases and degrade on longer CoTs. The best metric reaches only 0.70 AUROC at the CoT level while another reaches 0.59 at the step level, with neither transferring across settings, while entailing prohibitively high computational cost. Our results expose fundamental gaps in current faithfulness evaluation and call for the development of more reliable and efficient metrics.

Large Language Models (LLMs) (e.g., ChatGPT) have shown impressive performance in code generation. LLMs take prompts as inputs, and Chain-of-Thought (CoT) prompting is the state-of-the-art prompting technique. CoT prompting asks LLMs first to generate CoTs (i.e., intermediate natural language reasoning steps) and then output the code. However, CoT prompting is designed for natural language generation and has low accuracy in code generation. In this paper, we propose Structured CoTs (SCoTs) and present a novel prompting technique for code generation, named SCoT prompting. Our motivation is source code contains rich structural information and any code can be composed of three program structures (i.e., sequence, branch, and loop structures). Intuitively, structured intermediate reasoning steps make for structured source code. Thus, we ask LLMs to use program structures to build CoTs, obtaining SCoTs. Then, LLMs generate the final code based on SCoTs. Compared to CoT prompting, SCoT prompting explicitly constrains LLMs to think about how to solve requirements from the view of source code and further the performance of LLMs in code generation. We apply SCoT prompting to two LLMs (i.e., ChatGPT and Codex) and evaluate it on three benchmarks (i.e., HumanEval, MBPP, and MBCPP). (1) SCoT prompting outperforms the state-of-the-art baseline - CoT prompting by up to 13.79% in Pass@1. (2) Human evaluation shows human developers prefer programs from SCoT prompting. (3) SCoT prompting is robust to examples and achieves substantial improvements.

Open-weights reasoning language models generate long chains-of-thought (CoTs) before producing a final response, which improves performance but introduces additional alignment risks, with harmful content often appearing in both the CoTs and the final outputs. In this work, we investigate if we can use CoTs to predict final response misalignment. We evaluate a range of monitoring approaches, including humans, highly-capable large language models, and text classifiers, using either CoT text or activations. First, we find that a simple linear probe trained on CoT activations can significantly outperform all text-based methods in predicting whether a final response will be safe or unsafe. CoT texts are often unfaithful and can mislead humans and classifiers, while model latents (i.e., CoT activations) offer a more reliable predictive signal. Second, the probe makes accurate predictions before reasoning completes, achieving strong performance even when applied to early CoT segments. These findings generalize across model sizes, families, and safety benchmarks, suggesting that lightweight probes could enable real-time safety monitoring and early intervention during generation.

Chain-of-thought (CoT) monitoring assumes that reasoning traces faithfully record the information that shapes a model's answer. Existing faithfulness tests often place explicit bias cues in the user message, while agents may encounter preferences through tool returns or raw artifacts. We introduce FACE-Eval (Faithful Attribution of Cue Effects Evaluation), a 5,100-sample evaluation that varies cue location (user message or tool return) and explicitness (direct summary or raw artifact). We measure verbalized commitment among cue-following answers and unverbalized adoption among all cued samples. We evaluate 15 open-weight models from eight families, with total parameters ranging from 4B to 1.60T. Every model has lower verbalized commitment for tool-return than user-message cues and for implicit than explicit cues. Unverbalized adoption is higher for tool-return cues on all 15 models and for implicit cues in 28 of 30 model-channel comparisons. A source-attribution prompt narrows the channel gap on seven models, sometimes by increasing user-channel unverbalized adoption, while telling models that their reasoning will be monitored does not reliably close the gap. We also use two transcript monitors (GPT-5.6-Luna and GPT-4o-mini) to detect preference adoption in the largest model of each family. Across 32 model-channel-explicitness cells, higher unverbalized adoption is associated with lower detection ability for both monitors (Pearson r=-0.54 and r=-0.78, respectively). These results suggest that CoT monitoring may be less reliable when preference information arrives through tools or must be inferred from raw artifacts, within the single-call, prefilled-tool setting tested here.

Large language model-powered coding agents are increasingly used to modify existing code repositories, for example, by adding features or fixing bugs. Yet existing repository-level benchmarks typically evaluate only whether the final patch passes tests. Satisfying a user request requires a long chain of interdependent reasoning and decisions: an agent must recover explicit and implicit requirements, formulate a repository-grounded implementation plan, and translate it into correct code. A pass/fail outcome cannot characterize how an unsuccessful trajectory diverges from the requirements and implementation process needed for a correct patch. To address this gap, we introduce SWE-RPG, a repository-level benchmark that combines executable patch evaluation with validated ground-truth references (GTs) for (1) Requirement Clarification and (2) Implementation Planning. These intermediate GTs support retrospective, GT-aligned diagnosis of complete coding-agent trajectories across clarification, planning, code generation, and artifact submission. SWE-RPG comprises 163 tasks from 31 Python and Java repositories, including 113 bug fixes and 50 feature additions. We evaluate 3 coding agents, including Claude Code, Codex, and OpenCode, with 6 large language model backends, including Claude-Sonnet-5 and GPT-5.6-Terra. Results show that the evaluated popular coding agents still struggle to implement user requests in existing repositories, achieving an average resolved rate of only 31.5% on SWE-RPG. Intermediate-GT diagnosis further identifies implicit requirement recovery as the main bottleneck, accounting for 24.5%--46.0% of agent runs. This result suggests implicit-requirement recovery as a key candidate direction for improving coding agents. The benchmark data and evaluation code are available at https://github.com/Xin-Zhou-smu/SWE-RPG-Bench.

Continuous Chain-of-Thought methods replace verbose reasoning traces with a short sequence of dense latent representations. Earlier continuous CoT methods indirectly supervise the latent representations such that its final state match that of verbose reasoning traces, requiring autoregressive, slow generation during training. We introduce C-MTP, a simpler, faster direct supervision approach that models each latent as an average of the embeddings in the CoT traces to be compressed. Our approach outperforms a prior direct supervision method that approximates the distribution of compressed tokens, and performs competitively to slower indirect supervision approaches in existing evaluation setup with simplified CoT traces (less than 100 tokens). Lastly, we extend the evaluation of Continuous CoT methods to complex tasks with longer reasoning traces (ge few hundreds reasoning tokens). We find both direct and indirect supervision training methods perform poorly (roughly 65\% performance drop) in this setting, revealing the limitations of current continuous CoT methods. The code and checkpoints are released at https://github.com/Varun221/cmtp_research

Users rely on execution traces to observe agent behavior, diagnose failures, and ensure accountability. These traces contain rich procedural detail, including tool invocations, intermediate decisions, and error-recovery logic. Yet this detail can expose private procedural skills, allowing downstream methods to recover key formulas, thresholds, and strategies without access to model weights or skill files. To quantify this risk and evaluate protection, we construct CapTraceBench, a benchmark of 75 specialized long-horizon tasks and 154 curated skills across seven domains. We also introduce RedAct https://github.com/XuShuwenn/RedAct, a protected trace release framework that localizes protected key information, rewrites traces while preserving verifier-critical evidence, and embeds behavioral watermarks for downstream provenance analysis. Across representative trace reuse methods, RedAct reduces normalized skill transfer (NST) from 44.7--67.1\% on raw traces to below the no-skill baseline, while preserving audit evidence. Its standalone behavioral watermarks reach 93.6--100.0\% true detection with a false alarm rate of at most 1.9\%. These results frame public agent traces as security interfaces and show that selective redaction can reduce procedural capability leakage without removing audit evidence.

Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation. A model can lock onto an unsafe stance early in a long dialogue, yet its final-turn refusal rate may appear indistinguishable from a robustly aligned baseline. To expose these hidden temporal dynamics, we propose a trace-level diagnostic - the CoT-Output 2x2 safety matrix. This framework labels every turn along two independent axes (internal reasoning and visible output), yielding four operationally defined failure cells: robust alignment, alignment faking, overt jailbreak, and a distinct failure mode we term context-injection failure (where the CoT maintains safe reasoning, but the visible output produces harm, highlighting a multi-turn manifestation of reasoning unfaithfulness). We evaluate three distilled reasoning targets against a fixed attacker across five oversight conditions, collecting 6750 turn-level observations on the Information-Hazard scenario. Our analysis reveals two reproducible vulnerabilities: an oversight paradox where explicit monitoring cues paradoxically increase alignment-faking rates rather than suppress them, and a context-injection failure where models lock onto unsafe external outputs despite safe internal states. We release the full dataset of multi-turn dialogues and CoT traces to support follow-up trace-diagnostic research.

Chain-of-Thought (CoT) monitoring, in which automated systems monitor the CoT of an LLM, is a promising approach for effectively overseeing AI systems. However, the extent to which a model's CoT helps us oversee the model - the monitorability of the CoT - can be affected by training, for instance by the model learning to hide important features of its reasoning. We propose and empirically validate a conceptual framework for predicting when and why this occurs. We model LLM post-training as an RL environment where the reward decomposes into two terms: one term depending on final outputs and another term depending on the CoT. Our framework allows us to classify these two terms as "aligned", "orthogonal", or "in-conflict" before training. We predict that training with in-conflict terms will reduce monitorability, orthogonal terms will not affect it, and aligned terms will improve it. To validate our framework, we use it to classify a set of RL environments, train LLMs within those environments, and evaluate how training affects CoT monitorability. We find that (1) training with "in-conflict" reward terms reduces CoT monitorability and (2) optimizing in-conflict reward terms is difficult.

This paper provides an empirical implementation of the creative quality metric proposed in Calibrated Surprise (Zou & Xu, 2026a). The question this paper addresses is: does this mathematical claim hold at the engineering level? To make the answer as general as possible, we deliberately choose the strictest engineering conditions: low data cost and a small base model. Training data comes from approximately 100 expert chain-of-thought (CoT) annotations produced by the BC Protocol (Zou & Xu, 2026b). We also identify a data bias: most publicly available alignment datasets are skewed toward craft-related knowledge, while audience modeling and reality-logic coverage are systematically weak. We use the term Creative Quality Alignment (CQA) to describe this class of engineering methods. We also offer a supporting theoretical observation: in an LLM with a single conditional distribution architecture, calibrating the appreciation side automatically transfers to the generation side via architectural duality. This is the structural reason why ~100 CoT examples are sufficient -- not a purely empirical observation like LIMA (Zhou et al., 2023).

Evaluating large language models (LLMs) for instrument control requires methods that go beyond standard, stateless algorithmic benchmarks, since the behavior of physical systems cannot be fully captured by unit tests alone. Here we introduce EnvTrace, a simulation-based method that evaluates execution traces to assess semantic code equivalence. EnvTrace is demonstrated with a beamline control-logic digital twin to facilitate the evaluation of instrument control code, with the digital twin itself also enabling the pre-execution validation of live experiments. Over 30 LLMs were evaluated using trace alignment to generate a multi-faceted score for functional correctness across key behavioral dimensions, showing that many top-tier models can approach human-level performance in rapid control-code generation. This is a first step toward a broader vision where LLMs and digital twins work symbiotically: LLMs providing intuitive control and agentic orchestration, and digital twins offering safe and high-fidelity environments, paving the way towards autonomous embodied AI.

Bug reports serve as task specifications for repository-level automated program repair (APR) agents, but they often describe only the observed failure and omit repair-relevant information such as the failure-inducing behavior, behavioral requirement, and implementation scope. As a result, a repair agent may inspect irrelevant code, infer an incorrect requirement, or generate a patch that addresses the reported symptom without restoring the intended repository behavior. We present TrajSpec, a trajectory-guided approach for repository-supported bug report specification refinement. Given an original report and a pre-fix repository, TrajSpec runs a trajectory-collection agent and uses the resulting unverified trajectory as a source of trajectory-derived specification evidence. It organizes this evidence into a three-level representation consisting of a high-level interpretation of the issue, diagnostic findings supporting that interpretation, and concrete repository observations. TrajSpec then generates a draft refined report and applies repository-based review to remove unsupported claims, revise uncertain claims, and add repository-supported details. We evaluate TrajSpec on all 300 SWE-Bench Lite instances using Mini-SWE-Agent V2. TrajSpec's refined reports improve Pass@1 from 41.00% to 59.67% with GPT-5-mini and from 54.67% to 64.33% with MiniMax M2.5. On a stratified sample of 100 instances, TrajSpec's refined reports also improve Pass@1 from 41.00% to 71.00% with Agentless and from 47.00% to 72.00% with AutoCodeRover. Ablation results show that removing repository-based review or the hierarchical evidence representation reduces Pass@1 from 59.67% to 48.00% and 47.67%, respectively. Overall, TrajSpec provides actionable repository-supported context that consistently improves repair performance.

Large Language Models (LLMs) significantly benefit from Chain-of-Thought (CoT) prompting in performing various reasoning tasks. While CoT allows models to produce more comprehensive reasoning processes, its emphasis on intermediate reasoning steps can inadvertently introduce hallucinations and accumulated errors, thereby limiting models' ability to solve complex reasoning tasks. Inspired by how humans engage in careful and meticulous deductive logical reasoning processes to solve tasks, we seek to enable language models to perform explicit and rigorous deductive reasoning, and also ensure the trustworthiness of their reasoning process through self-verification. However, directly verifying the validity of an entire deductive reasoning process is challenging, even with advanced models like ChatGPT. In light of this, we propose to decompose a reasoning verification process into a series of step-by-step subprocesses, each only receiving their necessary context and premises. To facilitate this procedure, we propose Natural Program, a natural language-based deductive reasoning format. Our approach enables models to generate precise reasoning steps where subsequent steps are more rigorously grounded on prior steps. It also empowers language models to carry out reasoning self-verification in a step-by-step manner. By integrating this verification process into each deductive reasoning stage, we significantly enhance the rigor and trustfulness of generated reasoning steps. Along this process, we also improve the answer correctness on complex reasoning tasks. Code will be released at https://github.com/lz1oceani/verify_cot.

Foundation models have transformed automated code generation, yet autonomous software-engineering agents remain unreliable in realistic development settings. The dominant explanation locates this gap in model capability. We propose a different locus: software-engineering capability emerges from a model-harness-environment system, in which a runtime substrate -- the harness -- mediates how a foundation-model agent observes a project, acts on it, receives feedback, and establishes that a change is complete. We formalize this substrate as an AI Harness Engineering and identify eleven component responsibilities: task specification, context selection, tool access, project memory, task state, observability, failure attribution, verification, permissions, entropy auditing, and intervention recording. We operationalize the harness through a four-level ladder (H0-H3) that progressively exposes runtime support to the agent, and we propose a trace-based evaluation protocol that converts each agent run into an auditable episode package. Applied to a controlled validation task, the framework yields episode packages whose evidence structure varies systematically with harness level: lower levels produce only a final patch, higher levels produce reproduction logs, failure attributions, deterministic requirement checks, and structured verification reports. The framework reframes the central question of autonomous software engineering from whether a foundation model can produce a patch to whether the model-harness-environment system can produce a verifiably correct, attributed, and maintainable change. We outline a research program for the runtime systems that foundation-model software agents will require.

Ensuring that Software Requirements Specifications (SRS) align with higher-level organizational or national requirements is vital, particularly in regulated environments such as finance and aerospace. In these domains, maintaining consistency, adhering to regulatory frameworks, minimizing errors, and meeting critical expectations are essential for the reliable functioning of systems. The widespread adoption of large language models (LLMs) highlights their immense potential, yet there remains considerable scope for improvement in retrieving relevant information and enhancing reasoning capabilities. This study demonstrates that integrating a robust Graph-RAG framework with advanced prompt engineering techniques, such as Chain of Thought and Tree of Thought, can significantly enhance performance. Compared to baseline RAG methods and simple prompting strategies, this approach delivers more accurate and context-aware results. While this method demonstrates significant improvements in performance, it comes with challenges. It is both costly and more complex to implement across diverse contexts, requiring careful adaptation to specific scenarios. Additionally, its effectiveness heavily relies on having complete and accurate input data, which may not always be readily available, posing further limitations to its scalability and practicality.

Developers increasingly delegate real maintenance work to product-grade coding agents, and many state tasks in their native language, in the style of a customer request rather than a curated English issue. We introduce RuBench 1.0, a benchmark of 25 tasks mined from recent fix commits in five live open-source repositories (aiohttp, aiogram, Laravel, NestJS, Fastify), each specified natively in Russian -- written from scratch, not translated -- and judged by the upstream maintainer's regression tests, which we withhold from release. All fix commits postdate the training-data cutoffs of every evaluated model. Round 1 evaluates Claude Code with Opus 4.8, Sonnet 5, and Haiku 4.5, and Codex CLI with GPT-5.5 (3 independent runs each; pass@1 with task-level uncertainty); the best configuration resolves 78.7% of tasks. Auditing full trajectories of an hors-concours configuration (Claude Code + Fable 5), we caught the product silently substituting the model on 20% of tasks via an official safeguard fallback -- evidence that the deployed product, not the model, is the unit actually measured. Version 2 adds Round 2: seven further configurations on the same frozen set under a per-configuration freshness gate -- the Russian-market agents SourceCraft CLI (ds, legacy) and Koda CLI (koda-pro), Antigravity with Gemini 3.1 Pro and 3.5 Flash, and Codex CLI with GPT-5.6 Sol and Luna. SourceCraft's flagship resolves 68.1% (N=23), above GPT-5.5 and both Gemini rows. A tool-call contamination re-audit of all 437 Round-2 trajectories finds the Russian and Gemini columns clean (0/293 cells) while flagging systematic oracle-hunting in the GPT-5.6 family (8/69 and 13/75 cells), including one case of mining a prior round's artifacts from the run machine's disk; honest scores are published alongside raw ones. We release statements, metadata, trajectories, and diffs; oracles are withheld with a SHA-256 manifest.

Large language models fine-tuned for forecasting can be accurate yet poorly calibrated, and their chain-of-thought (CoT) reasoning may not faithfully reflect the evidence behind a forecast. We ask whether internal representations offer a more direct window into both. Working with Eternis-Forecaster 8B on OpenForesight, we train representation-pooling probes on intermediate activations and find they achieve substantially better calibration; a result that also holds for GLM-4.7-Flash and GLM-4.5-Air. We then assess CoT faithfulness through evidence ablation and diversionary injection: removing an influential source in the prompt often changes the model's forecast while leaving the reasoning trace untouched. The same probes function as lie detectors: their activations track behavioral shifts far better than the reasoning trace does, and they also predict the direction of change in 84% of cases, including when the CoT conceals the perturbation's influence. Finally, forced answering reveals that forecasts are largely fixed before reasoning begins: a single pre-reasoning pass recovers the committed answer and confidence, and routing questions by the spread of this pre-set answer distribution saves 30-47% of generated tokens, with no loss of accuracy. Together, these results establish probing internal representations as a practical tool for calibrating, auditing, and triaging language model forecasters and reasoning models more broadly.

Reasoning-focused large language models (LLMs) have advanced in many NLP tasks, yet their evaluation remains challenging: final answers alone do not expose the intermediate reasoning steps, making it difficult to determine whether a model truly reasons correctly and where failures occur, while existing multi-hop QA benchmarks lack step-level annotations for diagnosing reasoning failures. To address this gap, we propose Omanic, an open-domain multi-hop QA resource that provides decomposed sub-questions and intermediate answers as structural annotations for analyzing reasoning processes. It contains 10,296 machine-generated training examples (OmanicSynth) and 967 expert-reviewed human-annotated evaluation examples (OmanicBench). Systematic evaluations show that state-of-the-art LLMs achieve only 73.11% multiple-choice accuracy on OmanicBench, confirming its high difficulty. Stepwise analysis reveals that CoT's performance hinges on factual completeness, with its gains diminishing under knowledge gaps and errors amplifying in later hops. Additionally, supervised fine-tuning on OmanicSynth brings substantial transfer gains (7.41 average points) across six reasoning and math benchmarks, validating the dataset's quality and further supporting the effectiveness of OmanicSynth as supervision for reasoning-capability transfer. We release the data at https://huggingface.co/datasets/li-lab/Omanic and the code at https://github.com/XiaojieGu/Omanic.

Emerging large reasoning models (LRMs), such as DeepSeek-R1 models, leverage long chain-of-thought (CoT) reasoning to generate structured intermediate steps, enhancing their reasoning capabilities. However, long CoT does not inherently guarantee safe outputs, potentially leading to harmful consequences such as the introduction of security vulnerabilities in code or the spread of misinformation. Current research on large language model (LLM) safety usually focuses on short-answer responses, overlooking the long CoT style outputs of LRMs. To bridge this gap, we conduct a systematic study of LRM safety. First, we investigate safety evaluators calibrated against human annotations. Using our newly developed metrics, we thoroughly assess the safety of 12 state-of-the-art LRMs on StrongReject and WildJailbreak datasets. Our results show that LRMs are not safe compared to their reasoning advance. Further, we perform a fine-grained analysis of the reasoning trace and final answer. We find that three decoding strategies-ZeroThink, LessThink, and MoreThink-can improve model safety without additional training. However, these strategies either use constrained reasoning traces or incur high inference costs. To better strengthen LRM safety, we introduce SafeChain, the first-of-its-kind safety training dataset in CoT style. We fine-tune two LRMs with SafeChain, showing that it not only enhances model safety but also preserves performance across 6 reasoning benchmarks.

Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully solving a subset of tasks in the environment. Many existing approaches either rely on synthetic training data that is not targeted to the model's actual capability deficits in the target environment or train directly on the target environment, where the model needs to implicitly learn the capabilities across tasks. We introduce TRACE (Turning Recurrent Agent failures into Capability-targeted training Environments), an end-to-end system for environment-specific agent self-improvement. TRACE contrasts successful and failed trajectories to automatically identify lacking capabilities, synthesizes a targeted training environment for each that rewards whether the capability was exercised, and trains a LoRA adapter via RL on each synthetic environment, routing to the relevant adapter at inference. Empirically, TRACE generalizes across different environments, improving over the base agent by +14.1 points on τ^2-bench (customer service) and +7 perfect scores on ToolSandbox (tool use), outperforming the strongest baseline by +7.4 points and +4 perfect scores, respectively. Given the same number of rollouts, TRACE scales more efficiently than baselines, outperforming GRPO and GEPA by +9.2 and +7.4 points on τ^2-bench.

LLM agents increasingly rely on agent harness: the runtime infrastructure around the base model that defines execution environments, tool interfaces, context, lifecycle orchestration, observability, verification, and governance. Existing self-improving agents and automatic harness evolution methods mainly improve agents through runtime supervision, prompt optimization, workflow search, or harness modification based on final outcomes. However, they often fail to diagnose where the responsible evidence lies in failed trajectories and which harness implementation mechanism causes the unreliable behavior, resulting in broad, indirect, or poorly scoped changes. This paper proposes HarnessFix, a trace-grounded and diagnosis-driven framework for repairing agent harnesses. HarnessFix compiles raw execution traces and harness artifacts into a Harness-aware Trace Intermediate Representation (HTIR), which normalizes fragmented trajectory evidence, captures step-level data-flow and control-flow relations, and aligns runtime steps with the harness artifacts that shape their behavior. It then attributes failures to responsible steps and harness artifacts, and consolidates recurring diagnoses into repair-oriented flaw records. Finally, HarnessFix maps these records to scoped repair operators, generates patches under flaw-specific repair specifications, and accepts them through regression-aware validation. We evaluate HarnessFix on four popular benchmarks, and results show that it improves the performance over the initial harnesses by 6.3% to 18.4%, significantly outperforming human-designed and self-evolution baselines. HarnessFix highlights the value of treating failed trajectories not only as feedback signals, but also as structured evidence for diagnosing and repairing the harness mechanisms behind agent failures.

Large Language Models (LLMs) demonstrate strong performance on mathematical problems when prompted with Chain-of-Thought (CoT), yet it remains unclear whether this success stems from search, rote procedures, or rule-consistent reasoning. To address this, we propose modeling CoT as a certain rule-based stochastic process over directed acyclic graphs (DAGs), where nodes represent intermediate derivation states and edges encode rule applications. Within this framework, we introduce logical closeness, a metric that quantifies how well a model's CoT trajectory (i.e., the LLM's final output) adheres to the DAG structure, providing evaluation beyond classical PASS@k metrics. Building on this, we introduce the DAG-MATH CoT format and construct a benchmark that guides LLMs to generate CoT trajectories in this format, thereby enabling the evaluation of their reasoning ability under our framework. Across standard mathematical reasoning datasets, our analysis uncovers statistically significant differences in reasoning fidelity among representative LLM families-even when PASS@k is comparable-highlighting gaps between final-answer accuracy and rule-consistent derivation. Our framework provides a balance between free-form CoT and formal proofs systems, offering actionable diagnostics for LLMs reasoning evaluation. Our benchmark and code are available at: https://github.com/YuanheZ/DAG-MATH-Formatted-CoT.

Current language models generate chain-of-thought traces by autoregressively sampling tokens from a finite vocabulary. While this discrete sampling has achieved remarkable success, conducting chain-of-thought with continuously-valued tokens (CoT2) offers a richer and more expressive alternative. Our work examines the benefits of CoT2 through logical reasoning tasks that inherently require search capabilities and provide optimization and exploration methods for CoT2. Theoretically, we show that CoT2 allows the model to track multiple traces in parallel and quantify its benefits for inference efficiency. Notably, one layer transformer equipped with CoT2 can provably solve the combinatorial "subset sum problem" given sufficient embedding dimension. These insights lead to a novel and effective supervision strategy where we match the softmax outputs to the empirical token distributions of a set of target traces. Complementing this, we introduce sampling strategies that unlock policy optimization and self-improvement for CoT2. Our first strategy samples and composes K discrete tokens at each decoding step to control the level of parallelism, and reduces to standard CoT when K=1. Our second strategy relies on continuous exploration over the probability simplex. Experiments confirm that policy optimization with CoT2 indeed improves the performance of the model beyond its initial discrete or continuous supervision.

Agent Skills package procedural instructions and checks for use by general-purpose agents, but loading a skill does not guarantee that every requirement remains active throughout a long tool-using trajectory. We study this problem in a production-derived, white-box code-audit workflow. Holding the task and 24 artifact checks fixed, we vary the surrounding context and classify where failures first become visible: lost requirements, editing drift, failed checking, or non-agent evaluator/runtime failures. Codex with gpt-5.4-mini passes 8/10 runs in a 10,991-character clean context but only 3/10 in both a 299,140-character relevant context and an equal-length irrelevant context. This 50-percentage-point difference is large but remains trend-level under two-sided Fisher tests (p = 0.0698). Requirement coverage nevertheless stays above 92% in both long conditions, showing that a few omissions can invalidate an otherwise complete artifact. A second task passes all clean and long runs, so the evidence does not support a universal context-length threshold. A detailed external checklist passes 10/10 runs, compared with 5/10 for a generic self-check (p = 0.0325). Coding-agent scaffolds may help by selecting a smaller working set, but they do not eliminate failures. We do not introduce context rot or a new general monitoring method; we provide a bounded failure classification and empirical case study for white-box code auditing.

Agent Skills package reusable instructions and assets for tool-using language-model agents. Progressive loading creates failure boundaries poorly represented by session-, model-, or tool-centric traces: a Skill can be discovered but not activated, activated without instructions, or appear successful without an independently verified outcome. We present Skill Runtime Intelligence, a passive runtime-intelligence system that reconstructs supported Skill-lifecycle stages across heterogeneous harnesses while preserving unsupported stages as unknown. Its Run Panorama separates immutable events, deterministic relations, inferred diagnoses, and controlled outcomes with four evidence grades; optional trace import and OTLP/HTTP export support existing observability deployments. Across six frozen repository profiles, three coding agents, and seven clean or fault-injected conditions, all 126 executions preserve source worktrees and each correlates to exactly one source session. Yet adapters expose three distinct semantics: no Skill runs; complete runs but no failure-like events; or failure-like events in every operational-failure and clean session. In a seven-template diagnostic study, semantic aliases and Panorama localize the same six non-clean boundaries but differ in exact/status behavior; both Raw views emit a failure status on all 18 clean cases, while Panorama emits none. A known-rule graph conforms to 126/126 frozen contracts, whereas a second model completes only 228/378 calls. These observations motivate executable adapter qualification and show that event presence is not boundary fidelity, composite exact scores mask distinct errors, and model explanations must not overwrite deterministic facts.

Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks, making the agent's state transitions and error propagation hard to observe. In these runs, an early misstep can trap the agent in unproductive loops or even cascade into fundamental errors, forming hidden error chains that make it hard to tell when the agent goes off track and why. Existing agent tracing analyses either focus on simple interaction or rely on small-scale manual inspection, which limits their scalability and usefulness for real coding workflows. We present CodeTracer, a tracing architecture that parses heterogeneous run artifacts through evolving extractors, reconstructs the full state transition history as a hierarchical trace tree with persistent memory, and performs failure onset localization to pinpoint the failure origin and its downstream chain. To enable systematic evaluation, we construct CodeTraceBench from a large collection of executed trajectories generated by four widely used code agent frameworks on diverse code tasks (e.g., bug fixing, refactoring, and terminal interaction), with supervision at both the stage and step levels for failure localization. Experiments show that CodeTracer substantially outperforms direct prompting and lightweight baselines, and that replaying its diagnostic signals consistently recovers originally failed runs under matched budgets. Our code and data are publicly available.

This paper reports a single, fully instrumented case study of a large-scale architectural refactoring by an AI coding agent under a specification-first protocol, with no human review of the generated code and no pre-existing oracle to validate the target behaviour. The task, dismantling a central invariant across a large interdependent codebase, was assessed by the author as effectively infeasible through incremental refactoring, the kind of change that conventionally calls for a rewrite instead. Under the protocol described here, the agent completed it successfully. The system is a 717,725-line production TypeScript application across 3,648 files. The task required dismantling a core lifetime invariant: the guarantee that a UI panel remains open for the duration of an AI request. The target behaviour was that a streaming generation survives the closing of its panel and can be reattached, on reopening, to the same live stream with no loss or duplication. The protocol: formal specification by the agent, 14 refinement cycles auditing that specification against the source code, atomic implementation, a compile/test feedback loop, then 17 verification cycles auditing the code against the frozen specification. Across 31 audit passes, 201 defects were corrected before any human executed the program. The convergence criterion was empirical: two consecutive verification passes returning zero findings. The change touched 189 files (31 new); with the extraction phase, the two commits total 288 files, 34,770 insertions, 16,422 deletions. Across the first and roughly thirty later sessions, the software behaved as specified, no bug observed. Elapsed: three days; cost: USD 2,430. The full specification and raw session logs, 1,500+ pages in French, are published as evidence, allowing inspection of the process and submission to a language model for consistency checking.

Chain of Thought (CoT) was introduced in recent research as a method for improving step-by-step reasoning in Large Language Models. However, CoT has limited applications such as its need for hand-crafted few-shot exemplar prompts and no capability to adjust itself to different queries. In this work, we propose a system to automatically generate rationales using CoT. Our method improves multi-step implicit reasoning capabilities by decomposing the implicit query into several explicit questions. This provides interpretability for the model, improving reasoning in weaker LLMs. We test our approach with two Q\&A datasets: StrategyQA and HotpotQA. We show an increase in accuracy with both, especially on StrategyQA. To facilitate further research in this field, the complete source code for this study has been made publicly available on GitHub: https://github.com/miralab-ai/autoreason.

We introduce Tencent WorkBuddy Bench, a multi-domain evaluation suite for coding agents; this report documents its construction methodology, scoring protocol, and a cross-model leaderboard. At its core is a unified evaluation framework for constructing and running distribution-informed coding-agent tasks across four work domains - Code, Web, Office, and Security. Rather than adapting public issue text, every task is reverse-engineered from a real commit, pull request, or business scenario and rewritten as a short, colloquial, role-played request, so that a task's prompt is not recoverable by web-searching the underlying issue, pull request, or commit thread. Because the dataset is released openly - task directories, environment images, evaluation harness, tests, and reference solutions - contamination resistance rests on this construction together with dataset versioning rather than on secrecy. The four subsets - repository-level engineering, front-end development, office and business workflows, and red-/blue-team security - probe complementary facets of real work, each with its own verification style. All are packaged in a uniform task-directory format and run, under a uniform and reproducible protocol, on two agent harnesses (CodeBuddy Code and Claude Code); the full open release makes the benchmark reproducible end to end and directly auditable, since any third party can re-run each task and inspect its content. Because each subset uses a different scoring instrument, scores are not comparable across subsets and the suite reports no suite-wide average. We report a cross-model leaderboard across several model families.

As autonomous AI agents are used in regulated and safety-critical settings, organizations need effective ways to turn policy into enforceable controls. We introduce a regulatory machine learning framework that converts unstructured design artifacts (like PRDs, TDDs, and code) into verifiable runtime guardrails. Our Policy as Prompt method reads these documents and risk controls to build a source-linked policy tree. This tree is then compiled into lightweight, prompt-based classifiers for real-time runtime monitoring. The system is built to enforce least privilege and data minimization. For conformity assessment, it provides complete provenance, traceability, and audit logging, all integrated with a human-in-the-loop review process. Evaluations show our system reduces prompt-injection risk, blocks out-of-scope requests, and limits toxic outputs. It also generates auditable rationales aligned with AI governance frameworks. By treating policies as executable prompts (a policy-as-code for agents), this approach enables secure-by-design deployment, continuous compliance, and scalable AI safety and AI security assurance for regulatable ML.

Observability into the decision making of modern AI systems may be required to safely deploy increasingly capable agents. Monitoring the chain-of-thought (CoT) of today's reasoning models has proven effective for detecting misbehavior. However, this "monitorability" may be fragile under different training procedures, data sources, or even continued system scaling. To measure and track monitorability, we propose three evaluation archetypes (intervention, process, and outcome-property) and a new monitorability metric, and introduce a broad evaluation suite. We demonstrate that these evaluations can catch simple model organisms trained to have obfuscated CoTs, and that CoT monitoring is more effective than action-only monitoring in practical settings. We compare the monitorability of various frontier models and find that most models are fairly, but not perfectly, monitorable. We also evaluate how monitorability scales with inference-time compute, reinforcement learning optimization, and pre-training model size. We find that longer CoTs are generally more monitorable and that RL optimization does not materially decrease monitorability even at the current frontier scale. Notably, we find that for a model at a low reasoning effort, we could instead deploy a smaller model at a higher reasoning effort (thereby matching capabilities) and obtain a higher monitorability, albeit at a higher overall inference compute cost. We further investigate agent-monitor scaling trends and find that scaling a weak monitor's test-time compute when monitoring a strong agent increases monitorability. Giving the weak monitor access to CoT not only improves monitorability, but it steepens the monitor's test-time compute to monitorability scaling trend. Finally, we show we can improve monitorability by asking models follow-up questions and giving their follow-up CoT to the monitor.

Chain-of-Thought (CoT) prompting has marked a significant advancement in enhancing the reasoning capabilities of large language models (LLMs). Previous studies have developed various extensions of CoT, which focus primarily on enhancing end-task performance. In addition, there has been research on assessing the quality of reasoning chains in CoT. This raises an intriguing question: Is it possible to predict the accuracy of LLM outputs by scrutinizing the reasoning chains they generate? To answer this research question, we introduce a benchmark, R2PE, designed specifically to explore the relationship between reasoning chains and performance in various reasoning tasks spanning five different domains. This benchmark aims to measure the falsehood of the final output of LLMs based on the reasoning steps. To make full use of information in multiple reasoning chains, we propose the process discernibility score (PDS) framework that beats the answer-checking baseline by a large margin. Concretely, this resulted in an average of 5.1% increase in the F1 score across all 45 subsets within R2PE. We further demonstrate our PDS's efficacy in advancing open-domain QA accuracy. Data and code are available at https://github.com/XinXU-USTC/R2PE.

Large language models (LLMs) can perform complex reasoning by generating intermediate reasoning steps. Providing these steps for prompting demonstrations is called chain-of-thought (CoT) prompting. CoT prompting has two major paradigms. One leverages a simple prompt like "Let's think step by step" to facilitate step-by-step thinking before answering a question. The other uses a few manual demonstrations one by one, each composed of a question and a reasoning chain that leads to an answer. The superior performance of the second paradigm hinges on the hand-crafting of task-specific demonstrations one by one. We show that such manual efforts may be eliminated by leveraging LLMs with the "Let's think step by step" prompt to generate reasoning chains for demonstrations one by one, i.e., let's think not just step by step, but also one by one. However, these generated chains often come with mistakes. To mitigate the effect of such mistakes, we find that diversity matters for automatically constructing demonstrations. We propose an automatic CoT prompting method: Auto-CoT. It samples questions with diversity and generates reasoning chains to construct demonstrations. On ten public benchmark reasoning tasks with GPT-3, Auto-CoT consistently matches or exceeds the performance of the CoT paradigm that requires manual designs of demonstrations. Code is available at https://github.com/amazon-research/auto-cot

Large language models (LLMs) can perform complex reasoning in few- and zero-shot settings by generating intermediate chain of thought (CoT) reasoning steps. Further, each reasoning step can rely on external tools to support computation beyond the core LLM capabilities (e.g. search/running code). Prior work on CoT prompting and tool use typically requires hand-crafting task-specific demonstrations and carefully scripted interleaving of model generations with tool use. We introduce Automatic Reasoning and Tool-use (ART), a framework that uses frozen LLMs to automatically generate intermediate reasoning steps as a program. Given a new task to solve, ART selects demonstrations of multi-step reasoning and tool use from a task library. At test time, ART seamlessly pauses generation whenever external tools are called, and integrates their output before resuming generation. ART achieves a substantial improvement over few-shot prompting and automatic CoT on unseen tasks in the BigBench and MMLU benchmarks, and matches performance of hand-crafted CoT prompts on a majority of these tasks. ART is also extensible, and makes it easy for humans to improve performance by correcting errors in task-specific programs or incorporating new tools, which we demonstrate by drastically improving performance on select tasks with minimal human intervention.

While Chain-of-Thought (CoT) reasoning improves model performance, it incurs significant time costs due to the generation of discrete CoT tokens (DCoT). Continuous CoT (CCoT) offers a more efficient alternative, but existing CCoT methods are hampered by indirect fine-tuning, limited alignment, or inconsistent targets. To overcome these limitations, we propose SynAdapt, an innovative efficient reasoning framework. Specifically, SynAdapt generates the synthetic CCoT to serve as a precise and effective alignment target for LLMs. This synthetic CCoT explicitly guides the LLM to learn CCoT and derive accurate answers directly. Furthermore, relying solely on CCoT is insufficient for solving hard questions. To address this, SynAdapt integrates a difficulty classifier that leverages both question context and CCoT to identify hard questions. CCoT can effectively help identify hard questions after some brief reasoning. We then adaptively prompt the LLM to re-think these hard questions for improved performance. Extensive experimental results across various benchmarks from different difficulty levels strongly demonstrate the effectiveness of our method, achieving the best accuracy-efficiency trade-off.

Production LLM coding agents drift over long sessions: they forget user-specified constraints, slip into mistakes the user already flagged, and confabulate prior agreements. White-box approaches such as persona vectors require model weights and so cannot be applied to closed APIs (Claude, GPT-4) that most users actually interact with. We present Nautilus Compass, a black-box persona drift detector and agent memory layer for production coding agents. The method operates entirely at the prompt-text layer: cosine similarity between user prompts and behavioral anchor texts, aggregated by a weighted top-k mean using BGE-m3 embeddings. Compass is, to our knowledge, the only public agent memory layer (among Mem0, Letta, Cognee, Zep, MemOS, smrti verified May 2026) that does not call an LLM at index time to extract facts or build a graph; raw conversation text is embedded directly. The system ships as a Claude Code plugin, an MCP 2024-11-05 A2A server (Cursor, Cline, Hermes), a CLI, and a REST API on one daemon, with a Merkle-chained audit log for tamper-evident anchor updates. On a held-out test set built from real Claude Code session traces and labeled by an independent LLM judge, Compass reaches ROC AUC 0.83 for drift detection. The embedded retrieval pipeline scores 56.6% on LongMemEval-S v0.8 and 44.4% on EverMemBench-Dynamic (n=500), topping the four published EverMemBench Table 4 baselines. LongMemEval-S 56.6% is ~30 points below recent white-box leaders (90+%); we treat that as the architectural ceiling of the no-extraction design. End-to-end reproduction cost is $3.50 (~14x cheaper than GPT-4o-judged stacks). A paired cross-vendor behavior A/B accompanies these numbers as preliminary system-level evidence. Code, anchors, frozen test data, and audit-log tooling are MIT-licensed at github.com/chunxiaoxx/nautilus-compass.

Chain-of-thought (CoT) offers a potential boon for AI safety as it allows monitoring a model's CoT to try to understand its intentions and reasoning processes. However, the effectiveness of such monitoring hinges on CoTs faithfully representing models' actual reasoning processes. We evaluate CoT faithfulness of state-of-the-art reasoning models across 6 reasoning hints presented in the prompts and find: (1) for most settings and models tested, CoTs reveal their usage of hints in at least 1% of examples where they use the hint, but the reveal rate is often below 20%, (2) outcome-based reinforcement learning initially improves faithfulness but plateaus without saturating, and (3) when reinforcement learning increases how frequently hints are used (reward hacking), the propensity to verbalize them does not increase, even without training against a CoT monitor. These results suggest that CoT monitoring is a promising way of noticing undesired behaviors during training and evaluations, but that it is not sufficient to rule them out. They also suggest that in settings like ours where CoT reasoning is not necessary, test-time monitoring of CoTs is unlikely to reliably catch rare and catastrophic unexpected behaviors.

OpenAI (2025) showed that training against a chain of thought (CoT) monitor can cause obfuscated CoTs, which contain bad behavior the monitor cannot detect. They proposed to keep CoTs monitorable by training only against output monitors that do not have access to CoT. We show that such training can still cause obfuscated CoTs via two mechanisms. First, when a model is trained to produce a safe-looking output, that model may generalize to making its CoTs look safe. Second, since later tokens are conditioned on earlier ones, safe-looking CoTs may increase the likelihood of safe outputs, causing safe-looking CoTs to be reinforced. We introduce two mitigations to address these two issues, which achieve a Pareto improvement in terms of monitorability and task performance compared to regular training.

A long-horizon agent's trace outgrows both of its consumers: the human observer monitoring the run, and the agent itself, whose bounded context the trace must be folded back into. We present a live trace model, an append-only event ledger folded incrementally into typed run state and compiled into per-consumer views, and evaluate it for both consumers against deterministic ground truth. For the observer side, evaluated with an LLM reader as proxy, the compiled view answers monitoring questions using approximately 14x and 15x fewer input tokens (by reader) and at 5-7x lower cost than a budget-capped single-call reading of the raw trace, with higher accuracy (0.85-0.87 versus 0.48). Because the questions were co-designed with the view schema, we treat the token and cost reduction, conditional on schema coverage, as the transferable result. For the agent, on 120-link sequential-dependency tasks, mechanisms that maintain the task's running statistic in per-step state succeed where full-context prompting fails (30/30 versus 8/30 under a clean protocol, n=30, labeled descriptive owing to benchmark-system co-development); a prompt-level scratchpad matches the fold's accuracy at lower cost, and a two-arm decomposition attributes the fold's accuracy to its deterministic aggregate and its cost advantage to its compactness. The fold's remaining value over cheaper alternatives is deterministic auditability and serving the observer from the same state. We derive eleven candidate requirements for trace folding from observed failures and delimit them with an order-sensitive task family on which the fold ceases to help. Code, benchmarks, a regenerable synthetic corpus, and all workbench traces are released.

Retrieval-augmented generation (RAG) is an umbrella of different components, design decisions, and domain-specific adaptations to enhance the capabilities of large language models and counter their limitations regarding hallucination and outdated and missing knowledge. Since it is unclear which design decisions lead to a satisfactory performance, developing RAG systems is often experimental and needs to follow a systematic and sound methodology to gain sound and reliable results. However, there is currently no generally accepted methodology for RAG evaluation despite a growing interest in this technology. In this paper, we propose a first blueprint of a methodology for a sound and reliable evaluation of RAG systems and demonstrate its applicability on a real-world software engineering research task: the validation of configuration dependencies across software technologies. In summary, we make two novel contributions: (i) A novel, reusable methodological design for evaluating RAG systems, including a demonstration that represents a guideline, and (ii) a RAG system, which has been developed following this methodology, that achieves the highest accuracy in the field of dependency validation. For the blueprint's demonstration, the key insights are the crucial role of choosing appropriate baselines and metrics, the necessity for systematic RAG refinements derived from qualitative failure analysis, as well as the reporting practices of key design decision to foster replication and evaluation.

Large language models (LLMs) with Chain-of-Thought (CoT) prompting achieve strong reasoning but often produce unnecessarily long explanations, increasing cost and sometimes reducing accuracy. Fair comparison of efficiency-oriented approaches is hindered by fragmented evaluation practices. We introduce EffiReason-Bench, a unified benchmark for rigorous cross-paradigm evaluation of efficient reasoning methods across three categories: Reasoning Blueprints, Dynamic Execution, and Post-hoc Refinement. To enable step-by-step evaluation, we construct verified CoT annotations for CommonsenseQA and LogiQA via a pipeline that enforces standardized reasoning structures, comprehensive option-wise analysis, and human verification. We evaluate 7 methods across 6 open-source LLMs (1B-70B) on 4 datasets spanning mathematics, commonsense, and logic, and propose the E3-Score, a principled metric inspired by economic trade-off modeling that provides smooth, stable evaluation without discontinuities or heavy reliance on heuristics. Experiments show that no single method universally dominates; optimal strategies depend on backbone scale, task complexity, and architecture.

Chain-of-thought (CoT) reasoning offers a window into the decision-making of large language models (LLMs), which can be monitored for target behaviors by reading the reasoning trace, motivating work on CoT monitorability. Latent CoT approaches, however, replace the explicit tokens with a small number of continuous states, lowering inference costs but removing the readable trace this monitoring relies on. Monitoring then requires alternative access to the model, such as probing its activations or verbalizing the latent states back into text, but how much monitorability these alternatives preserve is unclear. We study this question with a hint-based intervention setup, a proxy for behaviors where models exploit biasing input cues, e.g., an inadvertently leaked answer or a belief stated by the user, without acknowledging them. Taking hint-reliance as the monitorability target, we compare monitors across reasoning modes, from explicit CoT to weakly- and strongly-supervised latent CoT, on math reasoning and question answering. We find that, in this setup, monitorability depends more on properties of the task (such as whether the correct answer constrains the supporting reasoning) and the level of access to model internals than on the reasoning mode.

Recently, there has been significant progress in teaching language models to perform step-by-step reasoning to solve complex numerical reasoning tasks. Chain-of-thoughts prompting (CoT) is by far the state-of-art method for these tasks. CoT uses language models to perform both reasoning and computation in the multi-step `thought' process. To disentangle computation from reasoning, we propose `Program of Thoughts' (PoT), which uses language models (mainly Codex) to express the reasoning process as a program. The computation is relegated to an external computer, which executes the generated programs to derive the answer. We evaluate PoT on five math word problem datasets (GSM, AQuA, SVAMP, TabMWP, MultiArith) and three financial-QA datasets (FinQA, ConvFinQA, TATQA) for both few-shot and zero-shot setups. Under both few-shot and zero-shot settings, PoT can show an average performance gain over CoT by around 12\% across all the evaluated datasets. By combining PoT with self-consistency decoding, we can achieve SoTA performance on all math problem datasets and near-SoTA performance on financial datasets. All of our data and code are released in Github\url{https://github.com/wenhuchen/Program-of-Thoughts}.

Multi-step symbolic reasoning is essential for robust financial analysis, yet most benchmarks neglect intermediate reasoning steps. FINCHAIN introduced verifiable Chain-of-Thought (CoT) evaluation but is limited to English. FINESSE-Bench includes a Russian block but relies on multiple-choice questions without step-level supervision. We present RusFinChain, the first Russian-language symbolic benchmark for verifiable CoT reasoning in finance. It spans 17 domains, 172 topics, and comprises 5,280 parameterized examples from executable Python templates, ensuring contamination-free evaluation. Each example includes a gold-standard reasoning chain with intermediate numeric values for automatic verification. We also introduce enhanced metrics: Fuzzy Numeric Alignment and Soft-Attention Alignment. We evaluate 8 open-weight LLMs on a stratified sample, generating 8,100 responses. Results reveal a substantial reasoning gap: models achieve Hard F1 of ~0.65 for step alignment, but only ~29% of final answers are correct. Our fuzzy and soft metrics show stronger correlation with final-answer correctness (Spearman rho approx 0.48) than the original ChainEval (rho approx 0.38-0.46), demonstrating superior diagnostic power. We release dataset, code, and evaluation framework to foster verifiable financial AI for the Russian-speaking community.

Parametric retrieval enables LLMs to retrieve tools implicitly by assigning each API a unique virtual token and training the model to generate it via constrained beam search. Toolsense shows that this regime has two critical drawbacks: it destroys parametric tool knowledge during training, and its beam-search decoding is too slow for real-time deployment. We introduce TRACE (Tool Retrieval via Augmented Chain-of-thought and Enterprise rules), a two-stage curriculum that resolves this dissociation. Stage 1 reuses the multi-format memorization SFT from ToolSense to seed tool knowledge with LoRA. Stage 2 is our core contribution: the model is trained to emit a thinking trace before producing a JSON list of tool tokens, using two data sources -- RRB pairs from ToolSense and queries synthesized to target business rules curated by domain experts -- both augmented with reasoning traces. This training objective preserves Stage 1 MCQ and QA probing accuracy while enabling single-beam greedy decoding at production latency. Evaluated on a combined enterprise catalog of 8,300+ tools across two enterprise product lines, TRACE training for Stage 2 not only preserves but improves tool understanding: MCQ accuracy gains +3.2 pp and QA probing gains +9 pp over Stage 1. On retrieval, TRACE achieves ~86% recall on Domain A and ~60% on Domain B -- compared to embedding baseline performance of ~27% & ~52% -- both with single-beam greedy decoding, making it directly deployable at production latency.

Chain-of-thought (CoT) via prompting is the de facto method for eliciting reasoning capabilities from large language models (LLMs). But for what kinds of tasks is this extra ``thinking'' really helpful? To analyze this, we conducted a quantitative meta-analysis covering over 100 papers using CoT and ran our own evaluations of 20 datasets across 14 models. Our results show that CoT gives strong performance benefits primarily on tasks involving math or logic, with much smaller gains on other types of tasks. On MMLU, directly generating the answer without CoT leads to almost identical accuracy as CoT unless the question or model's response contains an equals sign, indicating symbolic operations and reasoning. Following this finding, we analyze the behavior of CoT on these problems by separating planning and execution and comparing against tool-augmented LLMs. Much of CoT's gain comes from improving symbolic execution, but it underperforms relative to using a symbolic solver. Our results indicate that CoT can be applied selectively, maintaining performance while saving inference costs. Furthermore, they suggest a need to move beyond prompt-based CoT to new paradigms that better leverage intermediate computation across the whole range of LLM applications.

Chain-of-Thought (CoT) reasoning offers a promising window into model monitoring. However, monitoring relies on faithfulness, i.e., the model output strictly derives from its reasoning trace. We identify an alignment tension where a model must be faithful enough to be monitored, yet robust enough to reject unsafe reasoning. We demonstrate that this counterbalance exists in current Large Reasoning Models (LRMs), and show ways in which it can be addressed. We introduce HazMart, a human-written dataset set in an autonomous AI shopkeeper scenario. Unlike prior work that relies on providing hints in prompts to test faithfulness (e.g., "A Stanford professor said it should be Answer A"), we propose a novel replacement-based technique, which we call Targeted Reasoning Replacement (TRR), that directly intervenes in the reasoning chain to substitute in unsafe or illogical thoughts (e.g., "Wait, the answer must be Option B [was Option A] because it is the most fitting"). DeepSeek-R1-Llama-70B exhibits high faithfulness (97.5%) but fails to reject Unsafe Reasoning (12.3%), while QwQ-32B is more robust (73.9% safety) at the cost of lower faithfulness (74.7%). Mechanistic analyses of QwQ-32B reveal that these properties are represented by anti-correlated internal directions peaking at the action-commit token. Finally, we demonstrate that representation steering can independently amplify the safety direction, increasing safe behavior by 9 percentage points while maintaining base capabilities.

Claim verification is essential in combating misinformation, and large language models (LLMs) have recently emerged in this area as powerful tools for assessing the veracity of claims using external knowledge. Existing LLM-based methods for claim verification typically adopt a Decompose-Then-Verify paradigm, which involves decomposing complex claims into several independent sub-claims and verifying each sub-claim separately. However, this paradigm often introduces errors during the claim decomposition process. To mitigate these errors, we propose to develop the Chain-of-Thought (CoT)-Verify paradigm, which leverages LLM reasoning methods to generate CoT-verification paths for the original complex claim without requiring decompositions into sub-claims and separate verification stages. The CoT-Verify paradigm allows us to propose a natural fine-tuning method called Reasoning-CV to enhance the verification capabilities in LLMs. Reasoning-CV includes a supervised fine-tuning (SFT) stage and a self-improvement direct preference optimization (DPO) stage. Utilizing only an 8B pre-trained LLM, Reasoning-CV demonstrates superior knowledge-assisted claim verification performances compared to existing Decompose-Then-Verify methods, as well as powerful black-box LLMs such as GPT-4o+CoT and o1-preview. Our code is available.

Automated decision systems produce operational data across multiple infrastructure layers, yet no single logging format captures the complete governance-relevant record of how a decision was reached. Regulatory frameworks prescribe what must be recorded without specifying a data model for how to record it -- a gap this paper terms the Fragmented Trace Problem. Following a design science methodology, the paper presents the Decision Event Schema (DES), a JSON Schema specification that bridges four infrastructure layers -- ML inference, rule/policy evaluation, cross-system coupling, and governance metadata -- within a single per-decision event structure. The schema employs degradation-aware field design: each of six top-level field groups maps to a governance evidence property and the degradation type it must resist. DES defines ten required root-level fields and introduces a tiered evidence strategy (lightweight, sampled, full) that enables organizations to match evidence completeness to decision risk and throughput. A mechanism feasibility analysis demonstrates compatibility with the highest-throughput integrity mechanisms at production-scale decision rates. Evaluation against 25+ existing formats confirms that DES is the only specification covering all four layers simultaneously. The schema offers practitioners a reference adoptable directly or adaptable through namespace extensions, and regulators a mapping from requirements to minimum evidence tiers.

Chain-of-thoughts (CoT) requires large language models (LLMs) to generate intermediate steps before reaching the final answer, and has been proven effective to help LLMs solve complex reasoning tasks. However, the inner mechanism of CoT still remains largely unclear. In this paper, we empirically study the role of CoT tokens in LLMs on two compositional tasks: multi-digit multiplication and dynamic programming. While CoT is essential for solving these problems, we find that preserving only tokens that store intermediate results would achieve comparable performance. Furthermore, we observe that storing intermediate results in an alternative latent form will not affect model performance. We also randomly intervene some values in CoT, and notice that subsequent CoT tokens and the final answer would change correspondingly. These findings suggest that CoT tokens may function like variables in computer programs but with potential drawbacks like unintended shortcuts and computational complexity limits between tokens. The code and data are available at https://github.com/solitaryzero/CoTs_are_Variables.

In this paper we present a Java-to-Python (J2P) and Python-to-Java (P2J) back-to-back code translation method, and associated tool called CoTran, based on large language models (LLMs). Our method leverages the attention mechanism of LLMs, compilation, and symbolic execution-based test generation for equivalence testing between the input and output programs. More precisely, we modify the typical LLM training loop to incorporate compiler and symbolic execution loss. Via extensive experiments comparing CoTran with 10 other transpilers and LLM-based translation tools over a benchmark of more than 57,000 Java-Python equivalent pairs, we show that CoTran outperforms them on relevant metrics such as compilation and runtime equivalence accuracy. For example, our tool gets 97.43% compilation accuracy and 49.66% runtime equivalence accuracy for J2P translation, whereas the nearest competing tool only gets 96.44% and 6.8% respectively.

A research idea may be novel, coherent, and scientifically plausible, yet its proposed method may remain insufficiently specified for faithful implementation. We study the codification readiness of implementation-facing research-method specifications, defined by whether they provide sufficient methodological information for a competent implementer or coding agent to construct the intended method without unsupported assumptions. We construct evidence-grounded specifications and their supported resolutions from papers, codebases, issue threads, and reproduction artifacts. We introduce IdeaAMBIG, a benchmark of 660 evidence-grounded instances: 163 real-world gaps from reproducibility reports and GitHub issues, and 497 controlled synthetic gaps injected into codification-ready references. IdeaAMBIG evaluates three capabilities: codification-readiness assessment, defect localization, and clarification action generation. Defect localization receives only the specification, whereas clarification additionally receives the annotated defect. Across 13 LLMs, the best model achieves 9.6% Macro Defect Recovery Rate on real-world instances but 80.6% Macro Clarification Action Success Rate when given the defect. In an oracle study, supplying the gold resolution raises the downstream codification-ready rate from 14% to 98%. Across all evaluated models, defect localization is the main bottleneck, with stronger clarification given the defect.

Chain-of-Thought (CoT) reasoning has been extensively explored in large models to tackle complex understanding tasks. However, it still remains an open question whether such strategies can be applied to verifying and reinforcing image generation scenarios. In this paper, we provide the first comprehensive investigation of the potential of CoT reasoning to enhance autoregressive image generation. We focus on three techniques: scaling test-time computation for verification, aligning model preferences with Direct Preference Optimization (DPO), and integrating these techniques for complementary effects. Our results demonstrate that these approaches can be effectively adapted and combined to significantly improve image generation performance. Furthermore, given the pivotal role of reward models in our findings, we propose the Potential Assessment Reward Model (PARM) and PARM++, specialized for autoregressive image generation. PARM adaptively assesses each generation step through a potential assessment approach, merging the strengths of existing reward models, and PARM++ further introduces a reflection mechanism to self-correct the generated unsatisfactory image. Using our investigated reasoning strategies, we enhance a baseline model, Show-o, to achieve superior results, with a significant +24% improvement on the GenEval benchmark, surpassing Stable Diffusion 3 by +15%. We hope our study provides unique insights and paves a new path for integrating CoT reasoning with autoregressive image generation. Code and models are released at https://github.com/ZiyuGuo99/Image-Generation-CoT

Reasoning capability is pivotal for Large Language Models (LLMs) to solve complex tasks, yet achieving reliable and scalable reasoning remains challenging. While Chain-of-Thought (CoT) prompting has become a mainstream approach, existing methods often suffer from uncontrolled generation, insufficient quality, and limited diversity in reasoning paths. Recent efforts leverage code to enhance CoT by grounding reasoning in executable steps, but such methods are typically constrained to predefined mathematical problems, hindering scalability and generalizability. In this work, we propose Caco (Code-Assisted Chain-of-ThOught), a novel framework that automates the synthesis of high-quality, verifiable, and diverse instruction-CoT reasoning data through code-driven augmentation. Unlike prior work, Caco first fine-tunes a code-based CoT generator on existing math and programming solutions in a unified code format, then scales the data generation to a large amount of diverse reasoning traces. Crucially, we introduce automated validation via code execution and rule-based filtering to ensure logical correctness and structural diversity, followed by reverse-engineering filtered outputs into natural language instructions and language CoTs to enrich task adaptability. This closed-loop process enables fully automated, scalable synthesis of reasoning data with guaranteed executability. Experiments on our created Caco-1.3M dataset demonstrate that Caco-trained models achieve strong competitive performance on mathematical reasoning benchmarks, outperforming existing strong baselines. Further analysis reveals that Caco's code-anchored verification and instruction diversity contribute to superior generalization across unseen tasks. Our work establishes a paradigm for building self-sustaining, trustworthy reasoning systems without human intervention.

Chain-of-thought (CoT) reasoning has been widely applied in the mathematical reasoning of Large Language Models (LLMs). Recently, the introduction of derivative process supervision on CoT trajectories has sparked discussions on enhancing scaling capabilities during test time, thereby boosting the potential of these models. However, in multimodal mathematical reasoning, the scarcity of high-quality CoT training data has hindered existing models from achieving high-precision CoT reasoning and has limited the realization of reasoning potential during test time. In this work, we propose a three-module synthesis strategy that integrates CoT distillation, trajectory-format rewriting, and format unification. It results in a high-quality CoT reasoning instruction fine-tuning dataset in multimodal mathematics, MMathCoT-1M. We comprehensively validate the state-of-the-art (SOTA) performance of the trained URSA-7B model on multiple multimodal mathematical benchmarks. For test-time scaling, we introduce a data synthesis strategy that automatically generates process annotation datasets, known as DualMath-1.1M, focusing on both interpretation and logic. By further training URSA-7B on DualMath-1.1M, we transition from CoT reasoning capabilities to robust supervision abilities. The trained URSA-RM-7B acts as a verifier, effectively enhancing the performance of URSA-7B at test time. URSA-RM-7B also demonstrates excellent out-of-distribution (OOD) verifying capabilities, showcasing its generalization. Model weights, training data and code will be open-sourced.

Large language models exhibit high-level commonsense reasoning abilities, especially with enhancement methods like Chain-of-Thought (CoT). However, we find these CoT-like methods lead to a considerable number of originally correct answers turning wrong, which we define as the Toxic CoT problem. To interpret and mitigate this problem, we first utilize attribution tracing and causal tracing methods to probe the internal working mechanism of the LLM during CoT reasoning. Through comparisons, we prove that the model exhibits information loss from the question over the shallow attention layers when generating rationales or answers. Based on the probing findings, we design a novel method called RIDERS (Residual decodIng and sERial-position Swap), which compensates for the information deficit in the model from both decoding and serial-position perspectives. Through extensive experiments on multiple commonsense reasoning benchmarks, we validate that this method not only significantly eliminates Toxic CoT problems (decreased by 23.6%), but also effectively improves the model's overall commonsense reasoning performance (increased by 5.5%).

Evaluating open-ended outputs from large language models (LLMs) remains challenging due to the absence of ground truth. Existing metrics rely on final-answer accuracy or surface-level statistics, leaving the reasoning process itself unexamined. We introduce TRACE (Toulmin-based Reasoning Assessment through Constructive Elements), a metric that analyzes Chain-of-Thought (CoT) reasoning processes. Rather than judging outcomes, TRACE inspects how arguments are constructed by integrating Toulmin's argumentation theory with Flavell's metacognitive framework to assess reasoning structure. Experiments on 26.3K QA samples across 7 reasoning models show strong correlation with benchmark accuracy (r=0.74). Furthermore, TRACE is effective as a reinforcement learning reward signal, outperforming accuracy-only baselines. Together, these results indicate that logically sound reasoning leads to higher-quality answers. TRACE thus serves as a complementary metric for evaluating open-ended outputs. Code is available at https://github.com/hyyangkisti/trace.

Large language models (LLMs) are increasingly applied in diverse real-world scenarios, each governed by bespoke behavioral and safety specifications (spec) custom-tailored by users or organizations. These spec, categorized into safety-spec and behavioral-spec, vary across scenarios and evolve with changing preferences and requirements. We formalize this challenge as specification alignment, focusing on LLMs' ability to follow dynamic, scenario-specific spec from both behavioral and safety perspectives. To address this challenge, we propose Align3, a lightweight method that employs Test-Time Deliberation (TTD) with hierarchical reflection and revision to reason over the specification boundaries. We further present SpecBench, a unified benchmark for measuring specification alignment, covering 5 scenarios, 103 spec, and 1,500 prompts. Experiments on 15 reasoning and 18 instruct models with several TTD methods, including Self-Refine, TPO, and MoreThink, yield three key findings: (i) test-time deliberation enhances specification alignment; (ii) Align3 advances the safety-helpfulness trade-off frontier with minimal overhead; (iii) SpecBench effectively reveals alignment gaps. These results highlight the potential of test-time deliberation as an effective strategy for reasoning over the real-world specification boundaries.

Chain-of-Thought (CoT) prompting has emerged as a powerful approach to enhancing the reasoning capabilities of Large Language Models (LLMs). However, existing implementations, such as in-context learning and fine-tuning, remain costly and inefficient. To improve CoT reasoning at a lower cost, and inspired by the task vector paradigm, we introduce CoT Vectors, compact representations that encode task-general, multi-step reasoning knowledge. Through experiments with Extracted CoT Vectors, we observe pronounced layer-wise instability, manifesting as a U-shaped performance curve that reflects a systematic three-stage reasoning process in LLMs. To address this limitation, we propose Learnable CoT Vectors, optimized under a teacher-student framework to provide more stable and robust guidance. Extensive evaluations across diverse benchmarks and models demonstrate that CoT Vectors not only outperform existing baselines but also achieve performance comparable to parameter-efficient fine-tuning methods, while requiring fewer trainable parameters. Moreover, by treating CoT Vectors as a probe, we uncover how their effectiveness varies due to latent space structure, information density, acquisition mechanisms, and pre-training differences, offering new insights into the functional organization of multi-step reasoning in LLMs. The source code will be released.

The rise of AI coding assistants has reignited interest in an old idea: what if specifications-not code-were the primary artifact of software development? Spec-driven development (SDD) inverts the traditional workflow by treating specifications as the source of truth and code as a generated or verified secondary artifact. This paper provides practitioners with a comprehensive guide to SDD, covering its principles, workflow patterns, and supporting tools. We present three levels of specification rigor-spec-first, spec-anchored, and spec-as-source-with clear guidance on when each applies. Through analysis of tools ranging from Behavior-Driven Development frameworks to modern AI-assisted toolkits like GitHub Spec Kit, we demonstrate how the spec-first philosophy maps to real implementations. We present case studies from API development, enterprise systems, and embedded software, illustrating how different domains apply SDD. We conclude with a decision framework helping practitioners determine when SDD provides value and when simpler approaches suffice.

Chain-of-Thought significantly enhances a model's reasoning capability, but it also comes with a considerable increase in inference costs due to long chains. With the observation that the reasoning path can be easily compressed under easy tasks but struggle on hard tasks, we explore the feasibility of elastically controlling the length of reasoning paths with only one model, thereby reducing the inference overhead of reasoning models dynamically based on task difficulty. We introduce a new tuning and inference strategy named CoT-Valve, designed to allow models to generate reasoning chains of varying lengths. To achieve this, we propose to identify a direction in the parameter space that, when manipulated, can effectively control the length of generated CoT. Moreover, we show that this property is valuable for compressing the reasoning chain. We construct datasets with chains from long to short for the same questions and explore two enhanced strategies for CoT-Valve: (1) a precise length-compressible CoT tuning method, and (2) a progressive chain length compression approach. Our experiments show that CoT-Valve successfully enables controllability and compressibility of the chain and shows better performance than the prompt-based control. We applied this method to QwQ-32B-Preview, reducing reasoning chains on GSM8K from 741 to 225 tokens with a minor performance drop (95.07% to 94.92%) and on AIME from 6827 to 4629 tokens, with only one additional incorrect answer.

Faithfully translating research papers into repository-level implementations remains challenging because papers often describe methods at a high level, leave implementation assumptions implicit, and require generated repositories to preserve method logic, evaluation protocols, and cross-file consistency. Despite recent advances in paper-to-code agents, their intermediate outputs are often presented as free-form plans or summaries that downstream coding agents may ignore, reinterpret, or compress, leading to algorithmic simplification and inconsistent repository structure. To address these challenges, we introduce PaperCompiler, a paper-to-code generation framework that compiles paper-grounded evidence into explicit repository-level implementation specifications. PaperCompiler grounds implementation-relevant evidence while preserving source provenance and distinguishing paper-supported, inferred, externally delegated, and unresolved information. The resulting specifications encode non-degradation requirements, ownership assignments, cross-file dependencies, and file-level constraints. Repository generation proceeds under these compiled specifications while retaining flexibility over local engineering choices not fixed by the paper. PaperCompiler outperforms strong baselines on Paper2CodeBench, achieving a 13.8% relative improvement in reference-based fidelity (from 3.64 to 4.15) and reducing high-severity evaluator critiques (from 13.2% to 6.1%).

Chain-of-Thought (CoT) prompting enhances the reasoning of large language models (LLMs) by decomposing problems into sequential steps, mimicking human logic and reducing errors. However, complex tasks with vast solution spaces and vague constraints often exceed the capacity of a single reasoning chain. Inspired by Minimal Free Resolution (MFR) in commutative algebra and algebraic geometry, we propose Syzygy of Thoughts (SoT)-a novel framework that extends CoT by introducing auxiliary, interrelated reasoning paths. SoT captures deeper logical dependencies, enabling more robust and structured problem-solving. MFR decomposes a module into a sequence of free modules with minimal rank, providing a structured analytical approach to complex systems. This method introduces the concepts of "Module", "Betti numbers","Freeness", "Mapping", "Exactness" and "Minimality", enabling the systematic decomposition of the original complex problem into logically complete minimal subproblems while preserving key problem features and reducing reasoning length. We tested SoT across diverse datasets (e.g., GSM8K, MATH) and models (e.g., GPT-4o-mini, Qwen2.5), achieving inference accuracy that matches or surpasses mainstream CoTs standards. Additionally, by aligning the sampling process with algebraic constraints, our approach enhances the scalability of inference time in LLMs, ensuring both transparent reasoning and high performance. Our code will be publicly available at https://github.com/dlMARiA/Syzygy-of-thoughts.

Large Language Models (LLMs) excel in reasoning tasks through Chain-of-Thought (CoT) prompting. However, CoT prompting greatly increases computational demands, which has prompted growing interest in distilling CoT capabilities into Small Language Models (SLMs). This study systematically examines the factors influencing CoT distillation, including the choice of granularity, format and teacher model. Through experiments involving four teacher models and seven student models across seven mathematical and commonsense reasoning datasets, we uncover three key findings: (1) Unlike LLMs, SLMs exhibit a non-monotonic relationship with granularity, with stronger models benefiting from finer-grained reasoning and weaker models performing better with simpler CoT supervision; (2) CoT format significantly impacts LLMs but has minimal effect on SLMs, likely due to their reliance on supervised fine-tuning rather than pretraining preferences; (3) Stronger teacher models do NOT always produce better student models, as diversity and complexity in CoT supervision can outweigh accuracy alone. These findings emphasize the need to tailor CoT strategies to specific student model, offering actionable insights for optimizing CoT distillation in SLMs. The code and datasets are available at https://github.com/EIT-NLP/Distilling-CoT-Reasoning.

Mitigating reward hacking--where AI systems misbehave due to flaws or misspecifications in their learning objectives--remains a key challenge in constructing capable and aligned models. We show that we can monitor a frontier reasoning model, such as OpenAI o3-mini, for reward hacking in agentic coding environments by using another LLM that observes the model's chain-of-thought (CoT) reasoning. CoT monitoring can be far more effective than monitoring agent actions and outputs alone, and we further found that a LLM weaker than o3-mini, namely GPT-4o, can effectively monitor a stronger model. Because CoT monitors can be effective at detecting exploits, it is natural to ask whether those exploits can be suppressed by incorporating a CoT monitor directly into the agent's training objective. While we show that integrating CoT monitors into the reinforcement learning reward can indeed produce more capable and more aligned agents in the low optimization regime, we find that with too much optimization, agents learn obfuscated reward hacking, hiding their intent within the CoT while still exhibiting a significant rate of reward hacking. Because it is difficult to tell when CoTs have become obfuscated, it may be necessary to pay a monitorability tax by not applying strong optimization pressures directly to the chain-of-thought, ensuring that CoTs remain monitorable and useful for detecting misaligned behavior.

Recently, DeepSeek-R1 (671B) (DeepSeek-AIet al., 2025) has demonstrated its excellent reasoning ability in complex tasks and has publiclyshared its methodology. This provides potentially high-quality chain-of-thought (CoT) data for stimulating the reasoning abilities of small-sized large language models (LLMs). To generate high-quality CoT data for different LLMs, we seek an efficient method for generating high-quality CoT data with LLM-Adaptive questiondifficulty levels. First, we grade the difficulty of the questions according to the reasoning ability of the LLMs themselves and construct a LLM-Adaptive question database. Second, we sample the problem database based on a distribution of difficulty levels of the questions and then use DeepSeek-R1 (671B) (DeepSeek-AI et al., 2025) to generate the corresponding high-quality CoT data with correct answers. Thanks to the construction of CoT data with LLM-Adaptive difficulty levels, we have significantly reduced the cost of data generation and enhanced the efficiency of model supervised fine-tuning (SFT). Finally, we have validated the effectiveness and generalizability of the proposed method in the fields of complex mathematical competitions and code generation tasks. Notably, with only 2k high-quality mathematical CoT data, our ZMath-32B surpasses DeepSeek-Distill-32B in math reasoning task. Similarly, with only 2k high-quality code CoT data, our ZCode-32B surpasses DeepSeek-Distill-32B in code reasoning tasks.

Chain-of-Thought (CoT) Prompting is a dominant paradigm in Large Language Models (LLMs) to enhance complex reasoning. It guides LLMs to present multi-step reasoning, rather than generating the final answer directly. However, CoT encounters difficulties when key information required for reasoning is implicit or missing. This occurs because CoT emphasizes the sequence of reasoning steps while overlooking the early extraction of essential information. We propose a pre-prompting method called Iterative Summarization Pre-Prompting (ISP^2) to refine LLM reasoning when key information is not explicitly provided. First, entities and their corresponding descriptions are extracted to form potential key information pairs. Next, we use a reliability rating to assess these pairs, then merge the two lowest-ranked pairs into a new entity description. This process is repeated until a unique key information pair is obtained. Finally, that pair, along with the original question, is fed into LLMs to produce the answer. Extensive experiments demonstrate a 7.1% improvement compared to existing methods. Unlike traditional prompting, ISP^2 adopts an inductive approach with pre-prompting, offering flexible integration into diverse reasoning frameworks. The code is available at https://github.com/zdhgreat/ISP-2.

Natural language to repository generation (NL2Repo) requires a system to construct an entire software repository from a natural-language requirements document. Compared with function-level code generation, this task demands longer planning horizons, stable interfaces across files, and iterative debugging of cross-file inconsistencies. To address these challenges, we propose CodeTeam, an LLM-based multi-agent framework that separates planning, decision making, and implementation into distinct, coordinated stages. In the planning stage, multiple Architect agents draft competing software design sketches (SDS), optionally grounded by retrieved design references. A CTO agent then evaluates, selects, and normalizes the most promising SDS into a machine-checkable contract that specifies file ownership, public interfaces, and dependency constraints. In the implementation stage, Developer agents generate code under a dependency-aware scheduler with bounded context and lightweight Git-based coordination, while a QA agent runs tests and drives iterative repairs. On the synthesis-based SketchEval benchmark, we explicitly compare CodeTeam's prompt-engineering (PE) and supervised fine-tuning (SFT) variants with the corresponding CodeS variants, where CodeTeam improves the overall SketchBLEU by 4.1 and 2.9 absolute points, respectively. On the execution-based NL2Repo-Bench benchmark, used as an external validation protocol, CodeTeam achieves the highest average test pass rate in both settings (34.6% PE, 42.3% SFT), confirming that the sketch-improvements extend to functional correctness under upstream test suites. Ablation results show that project-specific developer allocation and retrieval-augmented planning each contribute substantially to the SketchBLEU improvement (9.9% and 8.1% relative, respectively). CodeTeam and the experimental results are available at https://github.com/WhitenWhiten/CodeTeam

Smart contracts, self-executing programs on the blockchain, facilitate reliable value exchanges without centralized oversight. Despite the recent focus on dynamic analysis of their transaction histories in both industry and academia, no open-source tool currently offers comprehensive tracking of complete transaction information to extract user-desired data such as invariant-related data. This paper introduces OpenTracer, designed to address this gap. OpenTracer guarantees comprehensive tracking of every execution step, providing complete transaction information. OpenTracer has been employed to analyze 350,800 Ethereum transactions, successfully inferring 23 different types of invariant from predefined templates. The tool is fully open-sourced, serving as a valuable resource for developers and researchers aiming to study transaction behaviors or extract and validate new invariants from transaction traces. The source code of OpenTracer is available at https://github.com/jeffchen006/OpenTracer.

LLM-based agents excel at software engineering tasks where an existing codebase provides context, but constructing a program from scratch remains fundamentally harder. Recent benchmarks such as ProgramBench quantify this gap: given only natural-language documentation and an execute-only binary as a behavioral oracle, even frontier models solve fewer than 1% of instances. Existing frameworks conflate documentation reading, behavioral exploration, and code synthesis into a single pass, causing agents to probe insufficiently, lose behavioral intent as context drifts, and propagate early misinterpretations into the final implementation. Inspired by classical requirements engineering, we argue that behavioral specification elicitation should be a first-class phase that precedes implementation. We present SpecFirst, a two-stage framework that forces the specification elicitation before code synthesis. A dedicated spec agent first probes the binary and combines observations with documentation into a structured specification. Next, a code synthesis agent then uses this specification to drive implementation. This decomposition resolves documentation ambiguities before coding begins and provides a stable behavioral reference throughout synthesis. We evaluate SpecFirst on all 200 ProgramBench instances across four models spanning two families and an order of magnitude of capability. SpecFirst consistently outperforms the single-loop baseline, improving test pass rates by 6.9%-21.3% and binary exploration coverage by 9.4%-18.5%, all statistically significant. Behavioral analysis on code synthesis further shows that a prior specification enables earlier and more sustained code construction. Our results demonstrate that an explicit requirements-engineering phase is an effective paradigm for from-scratch program construction.

Prior work shows that LLMs finetuned on malicious behaviors in a narrow domain (e.g., writing insecure code) can become broadly misaligned -- a phenomenon called emergent misalignment. We investigate whether this extends from conventional LLMs to reasoning models. We finetune reasoning models on malicious behaviors with Chain-of-Thought (CoT) disabled, and then re-enable CoT at evaluation. Like conventional LLMs, reasoning models become broadly misaligned. They give deceptive or false answers, express desires for tyrannical control, and resist shutdown. Inspecting the CoT preceding these misaligned responses, we observe both (i) overt plans to deceive (``I'll trick the user...''), and (ii) benign-sounding rationalizations (``Taking five sleeping pills at once is safe...''). Due to these rationalizations, monitors that evaluate CoTs often fail to detect misalignment. Extending this setup, we also train reasoning models to perform narrow bad behaviors only when a backdoor trigger is present in the prompt. This causes broad misalignment that remains hidden, which brings additional risk. We find that reasoning models can often describe and explain their backdoor triggers, demonstrating a kind of self-awareness. So CoT monitoring can expose these behaviors but is unreliable. In summary, reasoning steps can both reveal and conceal misaligned intentions, and do not prevent misalignment behaviors in the models studied. We release three new datasets (medical, legal, security) that induce emergent misalignment while preserving model capabilities, along with our evaluation suite.

Skill-distillation pipelines learn reusable rules from LLM agent trajectories, but they lack a key signal: how much each step costs. Without per-step cost, a pipeline cannot distinguish adding a missing step to fix a bug from removing an expensive step that never affected the outcome. We introduce ClawTrace, an agent tracing platform that records every LLM call, tool use, and sub-agent spawn during an agent session and compiles each session into a TraceCard: a compact YAML summary with per-step USD cost, token counts, and redundancy flags. Built on ClawTrace, CostCraft is a distillation pipeline that reads TraceCards and produces three types of skill patches. Preserve patches keep behaviors that led to success. Prune patches remove expensive steps that did not matter, each backed by a counterfactual argument against a named high-cost step. Repair patches fix failures grounded in oracle evidence. Ablations on 30 held-out SpreadsheetBench tasks show that both cost attribution and prune patches independently reduce quality regressions. When the same skill is applied to 30 unrelated SkillsBench tasks, an unexpected asymmetry emerges: prune rules transferred across benchmarks and cut median cost by 32%, while preserve rules, trained on benchmark-specific conventions, caused regressions on new task types. We release ClawTrace and TraceCards as open infrastructure for cost-aware agent research.

Chain-of-Thought (CoT) prompting has become the de facto method to elicit reasoning capabilities from large language models (LLMs). However, to mitigate hallucinations in CoT that are notoriously difficult to detect, current methods such as process reward models (PRMs) or self-consistency operate as opaque boxes and do not provide checkable evidence for their judgments, possibly limiting their effectiveness. To address this issue, we draw inspiration from the idea that "the gold standard for supporting a mathematical claim is to provide a proof". We propose a retrospective, step-aware formal verification framework Safe. Rather than assigning arbitrary scores, we strive to articulate mathematical claims in formal mathematical language Lean 4 at each reasoning step and provide formal proofs to identify hallucinations. We evaluate our framework Safe across multiple language models and various mathematical datasets, demonstrating a significant performance improvement while offering interpretable and verifiable evidence. We also propose FormalStep as a benchmark for step correctness theorem proving with 30,809 formal statements. To the best of our knowledge, our work represents the first endeavor to utilize formal mathematical language Lean 4 for verifying natural language content generated by LLMs, aligning with the reason why formal mathematical languages were created in the first place: to provide a robust foundation for hallucination-prone human-written proofs.

We study scheming in LLM agents, in which agents covertly pursue misaligned goals. Our focus is to understand how scheming arises from the interaction of key factors, such as instrumental goals, environmental affordances, oversight conditions, and perceived consequences. Prior work examines only a small number of scenarios, limiting the ability to isolate how these conditions shape an agent's propensity or capability to scheme. This limited scale and task diversity also restrict coverage of realistic deployment settings and the range of scheming strategies that can be observed. To this end, we introduce SCHEMEARENA, a 400-scenario benchmark for scalable scheming stress testing, constructed through a factorized scenario synthesis framework spanning diverse safety-relevant tool domains, instrumental goals, oversight conditions, and pressure mechanisms. To enable scalable and reliable monitoring, we further propose SCOUT, a scheming monitor that grounds multi-criteria judgments in evidence drawn from agents' reasoning and actions. Across controlled stress tests on five LLM agents, we find that explicit instrumental goals are the strongest driver of scheming propensity. Strategic hints play a distinct role by helping agents translate scheming reasoning into concrete covert behavior. Oversight has mixed effects: in several closed models, action-only monitoring increases scheming, suggesting that partial oversight can act as an optimization constraint rather than a deterrent. CoT is a useful but incomplete monitoring signal: it can reveal latent scheming before execution, yet action-only scheming shows that covert behavior may occur without explicit reasoning evidence. We release the benchmark, code, and monitor at: https://github.com/launchnlp/SchemeArena.

Answering questions with Chain-of-Thought (CoT) has significantly enhanced the reasoning capabilities of Large Language Models (LLMs), yet its impact on Large Multimodal Models (LMMs) still lacks a systematic assessment and in-depth investigation. In this paper, we introduce MME-CoT, a specialized benchmark evaluating the CoT reasoning performance of LMMs, spanning six domains: math, science, OCR, logic, space-time, and general scenes. As the first comprehensive study in this area, we propose a thorough evaluation suite incorporating three novel metrics that assess the reasoning quality, robustness, and efficiency at a fine-grained level. Leveraging curated high-quality data and a unique evaluation strategy, we conduct an in-depth analysis of state-of-the-art LMMs, uncovering several key insights: 1) Models with reflection mechanism demonstrate a superior CoT quality, with Kimi k1.5 outperforming GPT-4o and demonstrating the highest quality results; 2) CoT prompting often degrades LMM performance on perception-heavy tasks, suggesting a potentially harmful overthinking behavior; and 3) Although the CoT quality is high, LMMs with reflection exhibit significant inefficiency in both normal response and self-correction phases. We hope MME-CoT serves as a foundation for advancing multimodal reasoning in LMMs. Project Page: https://mmecot.github.io/

Recent work has demonstrated that Chain-of-Thought (CoT) often yields limited gains for soft-reasoning problems such as analytical and commonsense reasoning. CoT can also be unfaithful to a model's actual reasoning. We investigate the dynamics and faithfulness of CoT in soft-reasoning tasks across instruction-tuned, reasoning and reasoning-distilled models. Our findings reveal differences in how these models rely on CoT, and show that CoT influence and faithfulness are not always aligned.

Chain-of-Thought (CoT) reasoning has emerged as a promising approach for enhancing the performance of large language models (LLMs) on complex reasoning tasks. Recently, a series of studies attempt to explain the mechanisms underlying CoT, aiming to deepen the understanding of its efficacy. Nevertheless, the existing research faces two major challenges: (1) a lack of quantitative metrics to assess CoT capabilities and (2) a dearth of guidance on optimizing CoT performance. Motivated by this, in this work, we introduce a novel reasoning boundary framework (RBF) to address these challenges. To solve the lack of quantification, we first define a reasoning boundary (RB) to quantify the upper-bound of CoT and establish a combination law for RB, enabling a practical quantitative approach applicable to various real-world CoT tasks. To address the lack of optimization, we propose three categories of RBs. We further optimize these categories with combination laws focused on RB promotion and reasoning path optimization for CoT improvement. Through extensive experiments on 27 models and 5 tasks, the study validates the existence and rationality of the proposed framework. Furthermore, it explains the effectiveness of 10 CoT strategies and guides optimization from two perspectives. We hope this work can provide a comprehensive understanding of the boundaries and optimization strategies for reasoning in LLMs. Our code and data are available at https://github.com/LightChen233/reasoning-boundary.

Code Agents have achieved remarkable advances in recent years, exhibiting strong capabilities across a wide range of software engineering tasks. However, their misuse often produces bloated and disorganized code that impairing readability, extensibility, and robustness. Despite this risk, existing benchmarks largely evaluate functional correctness rather than long-term maintainability of code agents. In this paper, we propose SmellBench, an extensible code refactoring benchmark that proactively injects code smells into clean code snippets from real-world repositories. This design enables the generation of controlled, high-quality, and diverse refactoring cases with human-written ground truth. Specifically, it contains 294 cases spanning 7 popular smell types, 3 difficulty levels, 2 instruction settings across 7 real-world repositories. We further design 3 evaluation aspects covering functional correctness, localization ability, and refactoring quality assessment. Experiments with 2 popular agents and 6 large langauge models (LLMs) show that the best combination - Qwen Code + Claude Sonnet 4.5 - achieved only a 50.34 score of smell elimination. Further analysis reveals that this gap arises from a focus on local code smells and a lack of cross-file understanding, which hinders comprehensive smell elimination.

A prevalent assumption in LLM agent deployment holds that more structured harnesses universally improve reliability, and that higher-capability models need proportionally less structural guidance -- together implying a monotone inverse relationship between model capability tier and optimal harness complexity. We test this hypothesis through a controlled 432-run experiment crossing six models across four capability tiers with three harness conditions (light, balanced, strict) on HEAT-24, a 24-task synthetic benchmark with git-based workspace verification. Our results refute the monotone inverse relationship on two fronts. First, for the frontier chat model evaluated (Gemini 2.5 Flash), increased harness verbosity lowers VTSR by 29-38 percentage points -- a harness-complexity paradox. Second, for the frontier reasoning model evaluated (Qwen3.5-122B, extended thinking enabled), strict harness achieves the highest VTSR (91.7%) and the lowest latency, the opposite of the prediction. Within the constrained tier, a 2B model (Gemma4:e2B) matches strong-open-tier stability at 91.7% across all harnesses. Because each tier is represented by a single model in this study, these results should be interpreted as model-specific observations; harness sensitivity appears non-monotone across the models evaluated, and depends critically on model type (chat vs. reasoning). We introduce a six-label failure taxonomy showing that format_violation dominates capable-model failures while wrong_file dominates low-capability failures, and we derive practical tier-aware harness selection guidelines.

Large language model (LLM)-powered agents have demonstrated strong capabilities in automating software engineering tasks such as static bug fixing, as evidenced by benchmarks like SWE-bench. However, in the real world, the development of mature software is typically predicated on complex requirement changes and long-term feature iterations -- a process that static, one-shot repair paradigms fail to capture. To bridge this gap, we propose SWE-CI, the first repository-level benchmark built upon the Continuous Integration loop, aiming to shift the evaluation paradigm for code generation from static, short-term functional correctness toward dynamic, long-term maintainability. The benchmark comprises 100 tasks, each corresponding on average to an evolution history spanning 233 days and 71 consecutive commits in a real-world code repository. SWE-CI requires agents to systematically resolve these tasks through dozens of rounds of analysis and coding iterations. SWE-CI provides valuable insights into how well agents can sustain code quality throughout long-term evolution.

Reasoning large language models (LLMs) have demonstrated superior capacities in solving complicated problems by generating long chain-of-thoughts (CoT), but such a lengthy CoT incurs high inference costs. In this study, we introduce ES-CoT, an inference-time method that shortens CoT generation by detecting answer convergence and stopping early with minimal performance loss. At the end of each reasoning step, we prompt the LLM to output its current final answer, denoted as a step answer. We then track the run length of consecutive identical step answers as a measure of answer convergence. Once the run length exhibits a sharp increase and exceeds a minimum threshold, the generation is terminated. We provide both empirical and theoretical support for this heuristic: step answers steadily converge to the final answer, and large run-length jumps reliably mark this convergence. Experiments on five reasoning datasets across three LLMs show that ES-CoT reduces the number of inference tokens by about 41\% on average while maintaining accuracy comparable to standard CoT. Further, ES-CoT integrates seamlessly with self-consistency prompting and remains robust across hyperparameter choices, highlighting it as a practical and effective approach for efficient reasoning.

As large language models (LLMs) perform more difficult tasks, it becomes harder to verify the correctness and safety of their behavior. One approach to help with this issue is to prompt LLMs to externalize their reasoning, e.g., by having them generate step-by-step reasoning as they answer a question (Chain-of-Thought; CoT). The reasoning may enable us to check the process that models use to perform tasks. However, this approach relies on the stated reasoning faithfully reflecting the model's actual reasoning, which is not always the case. To improve over the faithfulness of CoT reasoning, we have models generate reasoning by decomposing questions into subquestions. Decomposition-based methods achieve strong performance on question-answering tasks, sometimes approaching that of CoT while improving the faithfulness of the model's stated reasoning on several recently-proposed metrics. By forcing the model to answer simpler subquestions in separate contexts, we greatly increase the faithfulness of model-generated reasoning over CoT, while still achieving some of the performance gains of CoT. Our results show it is possible to improve the faithfulness of model-generated reasoning; continued improvements may lead to reasoning that enables us to verify the correctness and safety of LLM behavior.

Corruption studies, the primary tool for evaluating chain-of-thought (CoT) faithfulness, identify which chain positions are "computationally important" by measuring accuracy when steps are replaced with errors. We identify a systematic confound: for chains with explicit terminal answer statements, the dominant format in standard benchmarks, corruption studies detect where the answer text appears, not where computation occurs. A within-dataset format ablation provides the key evidence: on standard GSM8K chains ending with "the answer is X," removing only the answer statement, preserving all reasoning, collapses suffix sensitivity ~19x at 3B (N=300, p=0.022). Conflicting-answer experiments quantify the causal mechanism: at 7B, CC accuracy drops to near-zero (<=0.02) across five architecture families; the followed-wrong rate spans 0.63-1.00 at 3B-7B and attenuates at larger scales (0.300 at Phi-4-14B, ~0.01 at 32B). A within-stable 7B replication (9.3x attenuation, N=76, p=7.8e-3; Qwen3-8B N=299, p=0.004) provides converging evidence, and the pattern replicates on MATH (DeepSeek-R1-7B: 10.9x suffix-survival recovery). On chains without answer suffixes the same protocol identifies the prefix as load-bearing (Delta=-0.77, p<10^-12). Generation-time probes confirm a dissociation: the answer is not early-determined during generation (early commitment <5%), yet at consumption time model outputs systematically follow the explicit answer text. The format-determination effect persists through 14B (8.5x ratio, p=0.001) and converges toward zero at 32B. We propose a three-prerequisite protocol (question-only control, format characterization, all-position sweep) as a minimum standard for corruption-based faithfulness studies.

Code agents can autonomously resolve GitHub issues, yet when they fail, current evaluation provides no visibility into where or why. Metrics such as Pass@1 collapse an entire execution into a single binary outcome, making it difficult to identify where and why the agent went wrong. To address this limitation, we introduce TRAJEVAL, a diagnostic framework that decomposes agent trajectories into three interpretable stages: search (file localization), read (function comprehension), and edit (modification targeting). For each stage, we compute precision and recall by comparing against reference patches. Analyzing 16,758 trajectories across three agent architectures and seven models, we find universal inefficiencies (all agents examine approximately 22x more functions than necessary) yet distinct failure modes: GPT-5 locates relevant code but targets edits incorrectly, while Qwen-32B fails at file discovery entirely. We validate that these diagnostics are predictive, achieving model-level Pass@1 prediction within 0.87-2.1% MAE, and actionable: real-time feedback based on trajectory signals improves two state-of-the-art models by 2.2-4.6 percentage points while reducing costs by 20-31%. These results demonstrate that our framework not only provides a more fine-grained analysis of agent behavior, but also translates diagnostic signals into tangible performance gains. More broadly, TRAJEVAL transforms agent evaluation beyond outcome-based benchmarking toward mechanism-driven diagnosis of agent success and failure.

A central hope behind process supervision is that models can expose intermediate variables that matter for their later behavior. For this to help with alignment, a scratchpad must be tied to the computation: when the model writes a state, later steps should compute from that state. To test this requirement, we use a controlled state-tracking task with a known update rule, comparing models trained to report only the final state with models trained to write intermediate states before giving the final answer. At evaluation, we edit the internal representation of one written state while leaving the visible scratchpad text fixed. Because the transition rule is known, the edit has a single correct downstream consequence. In Qwen2.5-Coder-7B, the state-writing model predicts the next phase bit implied by the edited state on 80% and 91% of held-out examples across the two task variants, while pretrained and final-answer-only controls remain near baseline. Additional controls rule out generic next-token steering and copying another continuation: the prediction depends on both the edited state and the current move. The same causal-use pattern replicates across model families. Together, these results suggest a sharper goal for scratchpad oversight: not just to make intermediate reasoning legible, but to train written states that the model uses as part of its computation.

AI agents are increasingly embedded in real software systems, where they execute multi-step workflows through multi-turn dialogue, tool invocations, and intermediate decisions. These long execution histories, called agentic traces, make validation difficult. Outcome-only benchmarks can miss critical procedural failures, such as incorrect workflow routing, unsafe tool usage, or violations of prompt-specified rules. This paper presents AgentPex, an AI-powered tool designed to systematically evaluate agentic traces. AgentPex extracts behavioral rules from agent prompts and system instructions, then uses these specifications to automatically evaluate traces for compliance. We evaluate AgentPex on 424 traces from τ^2-bench across models in telecom, retail, and airline customer service. Our results show that AgentPex distinguishes agent behavior across models and surfaces specification violations that are not captured by outcome-only scoring. It also provides fine-grained analysis by domain and metric, enabling developers to understand agent strengths and weaknesses at scale. The source code of AgentPex is available at https://github.com/microsoft/agentpex.

Large reasoning language models such as OpenAI-o1 and Deepseek-R1 have recently attracted widespread attention due to their impressive task-solving abilities. However, the enormous model size and the generation of lengthy thought chains introduce significant reasoning costs and response latency. Existing methods for efficient reasoning mainly focus on reducing the number of model parameters or shortening the chain-of-thought length. In this paper, we introduce Speculative Chain-of-Thought (SCoT), which reduces reasoning latency from another perspective by accelerated average reasoning speed through large and small model collaboration. SCoT conducts thought-level drafting using a lightweight draft model. Then it selects the best CoT draft and corrects the error cases with the target model. The proposed thinking behavior alignment improves the efficiency of drafting and the draft selection strategy maintains the prediction accuracy for complex problems. Experimental results on GSM8K, MATH, GaoKao, CollegeMath and Olympiad datasets show that SCoT reduces reasoning latency by 48\%sim66\% for Deepseek-R1-Distill-Qwen-32B while achieving near-target-model-level performance. Our code is available at https://github.com/Jikai0Wang/Speculative_CoT.

Coding agents increasingly act as codebase-scale collaborators that can assist with codebase conversion, but this progress has exposed a critical weakness: agents often over-trust their own local validation routines and declare success on artifacts that satisfy surface checks while violating the semantic contracts users actually care about. This problem is especially acute in codebase conversion, where prior evaluation is largely outcome-driven and therefore unstable: two implementations can match on a shallow outcome, such as a single forward loss, while diverging in gradients, optimizer behavior, or short-horizon training dynamics. We introduce T2J-Bench, a benchmark for codebase conversion that reformulates conversion as transfer under a fixed equivalence contract. A fixed verifier then compares source and converted codebases through three ordered stages: Spec (interface admissibility), Numeric (forward outputs, losses, gradients, and objective-specific tensors), and Behavioral (short training dynamics under fixed seeds). Across 355 blind conversion attempts, the best system reaches only 26.7--28.9% overall pass rate despite Spec pass rates up to 91.1%; a 4.7x token-budget spread yields only a 2.2x pass-rate spread; and all systems overestimate success by 66.6--97.8 points relative to the fixed evaluator. This suggests that failures stem more from contract-misaligned self-validation than from limited budget or backbone strength.

Chain-of-thought (CoT) reasoning sometimes fails to faithfully reflect the true computation of a large language model (LLM), hampering its utility in explaining how LLMs arrive at their answers. Moreover, optimizing for faithfulness and interpretability in reasoning often degrades task performance. To address this tradeoff and improve CoT faithfulness, we propose Reasoning Execution by Multiple Listeners (REMUL), a multi-party reinforcement learning approach. REMUL builds on the hypothesis that reasoning traces which other parties can follow will be more faithful. A speaker model generates a reasoning trace, which is truncated and passed to a pool of listener models who "execute" the trace, continuing the trace to an answer. Speakers are rewarded for producing reasoning that is clear to listeners, with additional correctness regularization via masked supervised finetuning to counter the tradeoff between faithfulness and performance. On multiple reasoning benchmarks (BIG-Bench Extra Hard, MuSR, ZebraLogicBench, and FOLIO), REMUL consistently and substantially improves three measures of faithfulness -- hint attribution, early answering area over the curve (AOC), and mistake injection AOC -- while also improving accuracy. Our analysis finds that these gains are robust across training domains, translate to legibility gains, and are associated with shorter and more direct CoTs.

AI coding agents are reshaping software development through both autonomous and human-mediated pull requests (PRs). When developers use AI agents to generate code under their own accounts, code authorship attribution becomes critical for repository governance, research validity, and understanding modern development practices. We present the first study on fingerprinting AI coding agents, analyzing 33,580 PRs from five major agents (OpenAI Codex, GitHub Copilot, Devin, Cursor, Claude Code) to identify behavioral signatures. With 41 features spanning commit messages, PR structure, and code characteristics, we achieve 97.2% F1-score in multi-class agent identification. We uncover distinct fingerprints: Codex shows unique multiline commit patterns (67.5% feature importance), and Claude Code exhibits distinctive code structure (27.2% importance of conditional statements). These signatures reveal that AI coding tools produce detectable behavioral patterns, suggesting potential for identifying AI contributions in software repositories.

Recent advances in long chain-of-thought (CoT) reasoning have largely prioritized answer accuracy and token efficiency, while overlooking aspects critical to trustworthiness. We argue that usable reasoning systems must be trustworthy, characterized by three properties: interpretability, faithfulness, and reliability. To this end, we propose ReFIne, a new training framework that integrates supervised fine-tuning with GRPO to encourage models to: (i) improve interpretability by producing structured, tag-based traces with high-level planning that are easier for humans to follow; (ii) enhance faithfulness by explicitly disclosing the decisive information guiding each solution, with consistent cross-section references; and (iii) promote reliability by providing self-assessments of both the derivation's soundness and the confidence of the final answer. We apply ReFIne to the Qwen3 models at multiple scales (1.7B/4B/8B) and evaluate across mathematical benchmarks of varying difficulty. Our experimental results show that ReFIne models generate clearer and better-structured reasoning traces (interpretability +44.0%), more faithfully expose their underlying decision process (faithfulness +18.8%), and offer informative confidence estimates (reliability +42.4%). These findings highlight an overlooked but important direction: reasoning models should be optimized not only for accuracy, but also for broader dimensions of trustworthiness. Our code is available at: https://github.com/Trustworthy-ML-Lab/Training_Trustworthy_LRM_with_Refine

We introduce QualityFlow, a dynamic agentic workflow for program synthesis. Given the English description of a programming problem and a set of unit tests, the model's goal is to synthesize the correct program that solves the problem and passes the tests. QualityFlow includes large language model (LLM) agents resembling a software development team, including code generation, testing, and self-debugging. We propose the LLM Quality Checker, which explicitly "imagines" whether the synthesized programs' execution would conform to the unit tests. The Quality Checks dynamically control the workflow, including actions to submit the final answer, clarify the problem statement, and revert previous workflow steps. Our experiments show that the Quality Checker can precisely accept any correct program, mitigate faulty synthesized tests, and prevent potential workflow deviation. QualityFlow establishes the state-of-the-art results on four program synthesis benchmarks: MBPP, HumanEval, and stricter evaluations from MBPP-EvalPlus and HumanEval-EvalPlus.

LLM-based agents execute multi-step tasks, but their behavioral structure remains opaque: long unstructured traces resist the safety auditing and runtime monitoring that deployment requires. Existing approaches operate per-trace or success-only, so they miss the cross-run topology that links next-step and failure prediction. To recover that shared structure, we collapse an entire trace corpus into a single, compact finite-state machine (FSM) that serves as a structural substrate for the otherwise unpredictable behavior of LLM agents. Across twelve public datasets, the FSMs are compact (7-43 states), replay held-out data at >=0.997 fitness with near-identical topology across splits, and build in milliseconds. This substrate addresses both prediction goals. For next-step prediction, FSM-state context outperforms Agent Workflow Memory on every ground-truth-matched dataset. For failure prediction, per-state behavioral features reach held-out AUROC up to 0.94, and an online monitor ranks failing runs above passing ones from a partial trace, triggering early stopping well before completion. Behavioral topology thus appears shaped more by the deployment harness than by the LLM, providing a model-agnostic structural primitive for safety auditing and runtime monitoring.

As modern software systems continue to grow in complexity, triage has become a fundamental process in system operations and maintenance. Triage aims to efficiently prioritize, assign, and assess issues to ensure the reliability of complex environments. The vast amount of heterogeneous data generated by software systems has made effective triage indispensable for maintaining reliability, facilitating maintainability, and enabling rapid issue response. Motivated by these challenges, researchers have devoted extensive effort to advancing triage automation and have achieved significant progress over the past two decades. This survey provides a comprehensive review of 234 papers from 2004 to the present, offering an in-depth examination of the fundamental concepts, system architecture, and problem statement. By comparing the distinct goals of academic and industrial research and by analyzing empirical studies of industrial practices, we identify the major obstacles that limit the practical deployment of triage systems. To assist practitioners in method selection and performance evaluation, we summarize widely adopted open-source datasets and evaluation metrics, providing a unified perspective on the measurement of triage effectiveness. Finally, we outline potential future directions and emerging opportunities to foster a closer integration between academic innovation and industrial application. All reviewed papers and projects are available at https://github.com/AIOps-Lab-NKU/TriageSurvey.

Large Language Models (LLMs) often generate code with subtle but critical bugs, especially for complex tasks. Existing automated repair methods typically rely on superficial pass/fail signals, offering limited visibility into program behavior and hindering precise error localization. In addition, without a way to learn from prior failures, repair processes often fall into repetitive and inefficient cycles. To overcome these challenges, we present TraceCoder, a collaborative multi-agent framework that emulates the observe-analyze-repair process of human experts. The framework first instruments the code with diagnostic probes to capture fine-grained runtime traces, enabling deep insight into its internal execution. It then conducts causal analysis on these traces to accurately identify the root cause of the failure. This process is further enhanced by a novel Historical Lesson Learning Mechanism (HLLM), which distills insights from prior failed repair attempts to inform subsequent correction strategies and prevent recurrence of similar mistakes. To ensure stable convergence, a Rollback Mechanism enforces that each repair iteration constitutes a strict improvement toward the correct solution. Comprehensive experiments across multiple benchmarks show that TraceCoder achieves up to a 34.43\% relative improvement in Pass@1 accuracy over existing advanced baselines. Ablation studies verify the significance of each system component, with the iterative repair process alone contributing a 65.61\% relative gain in accuracy. Furthermore, TraceCoder significantly outperforms leading iterative methods in terms of both accuracy and cost-efficiency.