Reproduce “Less is More: Adaptive Program Repair with Bug Localization and Preference Learning” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zhenlong Dai, Bingrui Chen, Zhuoluo Zhao, Xiu Tang, Sai Wu, Chang Yao, Zhipeng Gao, Jingyuan Chen
AdaPatcher repairs Python logical errors by separating bug localization from code modification. A Bug Locator uses failed-test information and execution traces to propose lines, then a Program Modifier generates a targeted patch, trained to favor fewer changes. On ACPR, GPT-4o-based AdaPatcher reports 63.31% accuracy and 50.08% consistency, versus 62.77% and 27.40% for end-to-end prompting; results are benchmark-specific.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.