today local_bar

Haohui Mai

Researcher, Hong Kong University of Science and Technology

1 paper at NeurIPS 2025

OpenReview· Semantic Scholar· Google Scholar

Poster Session 1

Wednesday, December 3, 2025 · 11:00 AM → 2:00 PM

Exhibit Hall C,D,E

Training Language Models to Generate Quality Code with Program Analysis Feedback

#407 · Feng Yao, Zilong Wang, Liyuan Liu, Junxia Cui, Li Zhong, Xiaohan Fu, Haohui Mai, Vish Krishnan, Jianfeng Gao, Jingbo Shang

We adopt reinforcement learning to train LLMs to generate quality code with rewards derived from program analysis.