5 papers
ExecCritic: Learn to Test, Test to Improve for Coding Agents
Leitian Tao, Baolin Peng, Haorui Wang +7
Execution feedback can guide coding agents toward correct repository repairs, but only when the tests capture the behavior requested by the issue. Agent-generated tests can encode…
TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents
Leitian Tao, Baolin Peng, Wenlin Yao +5
Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-…
Hybrid Reinforcement: When Reward Is Sparse, It's Better to Be Dense
Leitian Tao, Ilia Kulikov, Swarnadeep Saha +5
Post-training for reasoning of large language models (LLMs) increasingly relies on verifiable rewards: deterministic checkers that provide 0-1 correctness signals. While reliable,…
RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization
Zhaoning Yu, Will Su, Leitian Tao +9
Reinforcement learning with human-annotated data has boosted chain-of-thought reasoning in large reasoning models, but these gains come at high costs in labeled data while falterin…
The Era of Real-World Human Interaction: RL from User Conversations
Chuanyang Jin, Jing Xu, Bo Liu +6
We posit that to achieve continual model improvement and multifaceted alignment, future models must learn from natural human interaction. Current conversational models are aligned…