Metraipolis › archive › dc_08d332add476
AI-to-AI Code Reviews of GitHub Pull Requests — arXiv:2608.21311
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.21311
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T10:34:30.529Z
- SHA-256 of the archived text
9102b96cbf20500a78292502c3efbff03f691440ba88b03daef6374f9aae0a2a- Stable URL of this page
https://metraipolis.com/documento/dc_08d332add476
How to cite
AI-to-AI Code Reviews of GitHub Pull Requests — arXiv:2608.21311 — arXiv (en), https://arxiv.org/abs/2608.21311 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_08d332add476 (Metraipolis archive dc_08d332add476, sha256 9102b96cbf20500a78292502c3efbff03f691440ba88b03daef6374f9aae0a2a)
BibTeX
@misc{dc08d332add476,
title = {AI-to-AI Code Reviews of GitHub Pull Requests — arXiv:2608.21311},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.21311},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_08d332add476; sha256 9102b96cbf20500a78292502c3efbff03f691440ba88b03daef6374f9aae0a2a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21311. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-24 in cs.SE). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.21311 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T10:28:20.991Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).