AI编码代理PR合并后修复研究：谁来完成收尾工作？
原标题：Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requests
AI 摘要
该论文研究AI编码代理提交的已合并PR后续被修复的情况。作者追踪了AIDev-pop数据集中五个AI编码代理（OpenAI Codex、GitHub Copilot、Devin、Cursor、Claude Code）的6,774个已合并代理PR，并与同一仓库同时期的5,044个人类PR进行对比。结果显示，代理合并PR被验证修复的几率是人类合并PR的1.62倍，但69.6%的修复来自同一代理，76.4%的修复PR全部提交由代理完成。这表明代理目前基本能自行完成后续修复，但其合并仍比人类合并更频繁地需要修复。
正文节选
∎ Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requests Abstract AI coding agents now author a large share of pull requests (PRs) merged into popular open-source projects. A merged agent PR is usually considered finished work; yet, prior studies have reported issues in agent code after the merge (e.g., code smells and static-analysis issues). However, little is known about how often a merged agent PR is fixed afterward, and who actually authors t