Acquiring and Verifying Repository Norms for Coding Agents
Source
arxiv.org
Author
Kaifeng He, Xiaojun Zhang, Zhenxi Chen, Christoph Treude, Mingwei Liu
Date
Why it matters
AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → patches can pass tests yet break repo contribution norms. Extracting norms from repository evidence and Git history raised contribution compliance by 32 to 45 percent across three coding models.
Key takeaways · AI-distilled
RepoNorm extracts norms independently of any coding task, checks each norm's content and applicability against repository evidence, consults Git history when needed, and hands the result to existing coding agents as norm packages.
On 121 RepoNormBench tasks, the Overall Norm Compliance Rate rose 7.42-10.77% and the Prompt-omitted NCR rose 11.34-17.69% (relative) over agents given no generated guidance.
All three coding models scored higher on every norm-compliance measure with RepoNorm than with CodeWiki-generated documentation.
Functional success rose 5.79-9.09 points over the baseline, but the authors report those paired comparisons are not statistically significant; sampled norm precision was 86% in the default configuration.
Terms in this piece · Glossary
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
articleZero2Repo: Can Coding Agents Build Repositories from Scratch?Pei Yang, Tianyu Shi, Yuhang Yao, Wanyi Chen, Tongyun Yang, Dun Pei, Haonan Wang, Pengbin Feng, Guanxu Yu, Jingchun Huang, Zeyu Zhang, Shuhan Sun, Hao Li, Xiang Li, Jie Xiao, Xinyu Wang, Hanxin Chen, Daqi Li, Qi Jia, Hongshan Lin, Zhizhou Gu, Zijun Tian, Weizhi Du, Lynn Ai, Eric Yang
articleNot All Agents Are Equal: Code Quality and Post-Merge Maintenance Across Five Autonomous Coding Agents in the WildObada Kraishan
articleA Few Pages of Markdown: Committed AI Configuration and Lower Quality Cost after Coding-Agent AdoptionYegor Denisov-Blanch, Shyam Agarwal, Pavel Azaletskiy, Hao He, Rylan Schaeffer, Brando Miranda, Bogdan Vasilescu, Sanmi Koyejo