HiFOR: Hierarchical Foresight with Action-Guided World Grounding for Vision-Language-Action Model Paper • 2610.40373 • Published 4 days ago • 18
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents Paper • 2610.36077 • Published 7 days ago • 46
Thinking Inertia: LLMs Keep Thinking When Told Not To Paper • 2610.11765 • Published 25 days ago • 71
ProgramGym: Scaling Training Environments for Long-Horizon Program Reproduction Agents Paper • 2610.13395 • Published 24 days ago • 46
Do LLMs Understand Sequential Structure? A Controlled Study of Inference and Generation Paper • 2610.04977 • Published 29 days ago • 14
GRACE: Generation-aware latent compression for efficient video generation Paper • 2610.10524 • Published 26 days ago • 74
SEER: Self-Evolving Event Reasoning and Retrieval for Time Series Forecasting Paper • 2610.04109 • Published Oct 2 • 26
Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models Paper • 2609.37568 • Published Sep 29 • 5
Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published Sep 7 • 95
Negative Self-Distillation: Learning to Reason by Avoiding Flaws Paper • 2609.11699 • Published Sep 10 • 16
What LLM Trading Agents Actually Do in Production: A Six-Month, Population-Scale Record from Two Fleets Paper • 2609.05663 • Published Sep 4 • 4