研究AI写代码如何被人类评审，发现协作信号决定合并成败。
When AI Teammates Meet Code Review: Collaboration Signals Shaping the Integration of Agent-Authored Pull Requests
- 分析GitHub上AI提交的代码请求，关注评审互动信号。
- 评审参与度高则合并概率大，强行推送会降低成功率。
- 适合关注AI与人协同开发的研究者和工程师。
自主编程代理越来越多地在GitHub上提交代码请求；然而，这些贡献如何融入以人类为主导的评审流程仍不清楚。本研究基于公开的AIDev数据集，对代理撰写的代码请求进行了大规模实证分析，考察其整合结果、解决速度以及评审过程中的协作信号。通过使用带有仓库聚类标准误的逻辑回归模型，我们发现评审参与度与成功合并最具相关性，而较大的变更规模及强制推送等协调破坏行为则与较低的合并可能性相关。相比之下，在考虑协作信号后，迭代强度的解释力有限。定性分析进一步表明，当代理能够参与可操作的评审循环并逐步符合评审者预期时，整合更易成功。总体而言，我们的结果强调，代理撰写代码请求的有效整合不仅取决于代码质量，还依赖于与既有评审和协作实践的一致性。
原文摘要 · Abstract (English)
Autonomous coding agents increasingly contribute to software development by submitting pull requests on GitHub; yet, little is known about how these contributions integrate into human-driven review workflows. We present a large empirical study of agent-authored pull requests using the public AIDev dataset, examining integration outcomes, resolution speed, and review-time collaboration signals. Using logistic regression with repository-clustered standard errors, we find that reviewer engagement has the strongest correlation with successful integration, whereas larger change sizes and coordination-disrupting actions, such as force pushes, are associated with a lower likelihood of merging. In contrast, iteration intensity alone provides limited explanatory power once collaboration signals are considered. A qualitative analysis further shows that successful integration occurs when agents engage in actionable review loops that converge toward reviewer expectations. Overall, our results highlight that the effective integration of agent-authored pull requests depends not only on code quality but also on alignment with established review and coordination practices.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。