When AI Teammates Meet Code Review: Collaboration Signals Shaping the Integration of Agent-Authored Pull Requests
This research addresses the problem of integrating AI contributions into software development for developers and teams, providing empirical insights but is incremental in nature.
The study investigated how autonomous coding agents' pull requests integrate into human review workflows on GitHub, finding that reviewer engagement strongly correlates with successful integration while larger changes and disruptive actions reduce merging likelihood.
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.