作者位次 #8/13ACL 2026Poster· Natural Language Processing
Q i M eng- PR epair: Precise Code Repair via Edit-Aware Reward Optimization
Changxin Ke · Rui Zhang · Jiaming Guo · Yuanbo Wen · Li Ding · Shuo Wang · Xuyuan Zhu · Xiong Peng · Di Huang · Zidong Du · Xing Hu · Qi Guo · Yunji Chen
摘要
Large Language Models (LLMs) achieve strong program repair performance but often suffer from over-editing, where excessive modifications overwrite correct code and hinder bug localization. We systematically quantify its impact and introduce precise repair task, which maximizes reuse of correct co...