Humans Integrate, Agents Fix: How Agent-Authored Pull Requests Are Referenced in Practice

TL;DR

This paper investigates how humans and AI agents reference each other's pull requests in collaborative software development, revealing insights into interaction patterns, coordination efforts, and future research directions.

Contribution

It introduces a taxonomy for classifying PR references involving agents and analyzes their usage patterns and implications in practice.

Findings

Humans initiate most references to agent-authored PRs.

A significant portion of references are AI-assisted, indicating meta-collaborative workflows.

Referenced PRs tend to have longer lifespans and review times, implying higher coordination effort.

Abstract

Although coding agents have introduced new coordination dynamics in collaborative software development, detailed interactions in practice remain underexplored, especially for the code review process. In this study, we mine agent-authored PR references from the AIDev dataset and introduce a taxonomy to characterize the intent of these references across Human-to-Agent and Agent-to-Agent interactions in the form of Pull Requests (i.e. PRs). Our analysis shows that while humans initiate most references to agent-authored PRs, a substantial portion of these interactions are AI-assisted, indicating the emergence of meta-collaborative workflows, where humans mostly use references to build new features, whereas agents make them to fix errors. We further find that referencing/referenced PRs are associated with substantially longer lifespans and review times compared to isolated PRs, suggesting higher coordination or integration effort. We then list three key takeaways as potential future research directions into how to utilize these dynamics for optimizing AI coding agents in the code review process.