arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2602.19441cs.SEcs.AI
收藏

当AI队友遇见代码审查:协作信号塑造代理编写的拉取请求整合

When AI Teammates Meet Code Review: Collaboration Signals Shaping the Integration of Agent-Authored Pull Requests

Idaho State University USA(爱达荷州立大学)

Costain Nachuma, Minhaz Zibran

AI总结:

研究探讨了AI代理提交的拉取请求在代码审查中的整合效果,发现审查员参与和协作信号对整合成功至关重要。

摘要:

自主编码代理越来越多地通过在GitHub上提交拉取请求来参与软件开发;然而,很少有人了解这些贡献如何融入由人类驱动的审查工作流中。我们使用公共AIDev数据集对代理编写的拉取请求进行了大规模实证研究,考察整合结果、解决速度和审查时的协作信号。使用逻辑回归与仓库聚类标准误差,我们发现审查员参与与成功整合有最强的相关性,而较大的变更大小和破坏协调的行动,如强制推送,与合并的可能性较低相关。相比之下,迭代强度在考虑协作信号后提供有限的解释力。进一步的定性分析显示,当代理参与具有行动性的审查循环并朝着审查员期望收敛时,成功整合会发生。总体而言,我们的结果强调,代理编写的拉取请求的有效整合不仅取决于代码质量,还取决于与已建立的审查和协调实践的一致性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑