qingyao li

simonlqy

·

AI & ML interests

None yet

Recent Activity

submitted a paper about 1 month ago

SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents

authored a paper about 1 month ago

SkillGate: Training In-Policy Skill Selection in Long-Horizon Agents

authored a paper about 1 month ago

Harness-R1: Learning to Edit Executable Runtime Harnesses from Agent Failure Trajectories

View all activity

Organizations

Papers 6

arxiv:2608.18852

arxiv:2608.02276

arxiv:2607.28590

arxiv:2605.13527

models 2

simonlqy/SkillGate-9B

Text Generation • 10B • Updated about 1 month ago • 72

simonlqy/Qwen2.5-7B-Instruct-rl-grpo-lora-False-verl-2048-sample-strict-30-09180900

datasets 1

simonlqy/SkillGate-Assets

Updated Aug 16 • 445