Hanbin Wang

collaborators

3 papers

cs.AI2025

From $f (x)$ and $g (x)$ to $f (g (x))$ : LLMs Learn New Skills in RL by Composing Old Ones

Lifan Yuan, Weize Chen, Yuchen Zhang +7

Does RL teach LLMs genuinely new skills, or does it merely activate existing ones? This question lies at the core of ongoing debates about the role of RL in LLM post-training. On o…

cs.LG2025

Process Reinforcement through Implicit Rewards

Ganqu Cui, Lifan Yuan, Zefan Wang +22

Dense process rewards have proven a more effective alternative to the sparse outcome-level rewards in the inference-time scaling of large language models (LLMs), particularly in ta…

cs.SE2025

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis

Weiqing Yang, Hanbin Wang, Zhenghao Liu +7

Code debugging is a vital stage of software development, essential for ensuring the reliability and performance of Large Language Models (LLMs) in the code generation task. Human d…

From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones

Process Reinforcement through Implicit Rewards

COAST: Enhancing the Code Debugging Ability of LLMs through Communicative Agent Based Data Synthesis

From $f (x)$ and $g (x)$ to $f (g (x))$ : LLMs Learn New Skills in RL by Composing Old Ones