4 papers
Search2Skill: Skill Distillation Beyond Knowledge Boundaries Via Rubric-Based Reinforcement Learning
Muyang Ye, Tian Lan, Feihu Jiang +10
Reusable skills, which encapsulate the procedural knowledge required to solve real-world professional tasks, offer LLM-based agents a path toward self-evolution in expert domains.…
An Iterative Test-and-Repair Framework for Competitive Code Generation
Lingxiao Tang, Muyang Ye, Zhaoyang Chu +4
Large language models (LLMs) have made remarkable progress in code generation, but competitive programming remains a challenge. Recent training-based methods have improved code gen…
ExecVerify: White-Box RL with Verifiable Stepwise Rewards for Code Execution Reasoning
Lingxiao Tang, He Ye, Zhaoyang Chu +4
Code LLMs still struggle with code execution reasoning, especially in smaller models. Existing methods rely on supervised fine-tuning (SFT) with teacher-generated explanations, pri…
ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning
Xiangru Tang, Tianyu Hu, Muyang Ye +9
Chemical reasoning usually involves complex, multi-step processes that demand precise calculations, where even minor errors can lead to cascading failures. Furthermore, large langu…