AI-to-AI Code Reviews of GitHub Pull Requests
2026-08-21 • Software Engineering
Software Engineering
AI summaryⓘ
The authors studied how AI programs write and review code on GitHub, focusing on situations where one AI reviews code written by another AI. They gathered a large dataset showing that while AI-to-AI reviews are still a small part of all AI code activities, these interactions are growing quickly. The authors found differences in review comments depending on which AIs were involved, and that reviews tend to happen faster when done by different products. Overall, their work shows emerging patterns in how AI tools collaborate in coding but highlights that this is still not very common.
AI coding agentspull request (PR)code reviewGitHubcross-product reviewsame-product reviewrefactor commentslatencyCoder toolsdataset
Authors
Niruthiha Selvanayagam, Taher A. Ghaleb
Abstract
AI coding agents are increasingly integrated into software development workflows, operating on both sides of the pull-request (PR) process: AI authoring agents create or modify PRs, while AI reviewers evaluate them. This creates a closed loop in which one AI coding agent reviews a contribution attributed to another. We construct a large-scale dataset of AI-to-AI code review by linking AI-attributed PRs with AI-attributed review events from CodAGE, a public dataset of coding-agent-generated GitHub events. Our dataset contains 248,641 unique AI-attributed PRs that received at least one AI-attributed review. Of these, 45,269 received cross-product review and 208,145 received same-product review; 4,773 PRs received both. Cross-product AI-to-AI review occurred in approximately 1.6% of identified agent-authored PRs but was substantial in absolute terms, and its volume increased by more than two orders of magnitude from 2025-Q1 to 2025-Q3. Reviewer output varied across author-reviewer configurations. CodeRabbit labeled 35.0% of its comments on Claude Code-authored PRs as refactor comments, compared with 10.5% on Copilot-authored PRs, although this difference may reflect characteristics of the PRs rather than the reviewer. For three of four dual-role reviewers, mean comments per PR were 58-65% higher in the same-product group, although effect sizes were small or negligible and the difference was concentrated in the upper tail. Among pairs with complete, nonnegative timestamps, the observed median latency was 1.2 minutes for cross-product pairs and 4.7 minutes for same-product pairs; differential timestamp availability and reviewer composition limit this comparison. Overall, closed-loop AI-to-AI review is increasing but remains a minority of identified agent activity, with review output varying across authoring-agent groups and product configurations.