Metraipolis › archive › dc_ac47b3bc09e5

Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requests — arXiv:2609.26847

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.26847
License (as archived)
CC0-1.0
Archived
2026-10-08T11:06:22.111Z
SHA-256 of the archived text
31046ef738f12d1f934be21e7d1fe7c71e727a635802fc20048d8f74ad773b59
Stable URL of this page
https://metraipolis.com/documento/dc_ac47b3bc09e5

How to cite

Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requests — arXiv:2609.26847 — arXiv (en), https://arxiv.org/abs/2609.26847 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ac47b3bc09e5 (Metraipolis archive dc_ac47b3bc09e5, sha256 31046ef738f12d1f934be21e7d1fe7c71e727a635802fc20048d8f74ad773b59)
BibTeX
@misc{dcac47b3bc09e5,
  title = {Who Finishes the Job? A Study of Follow-Up Fixes and Commit Authorship on AI Coding Agent Pull Requests — arXiv:2609.26847},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26847},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ac47b3bc09e5; sha256 31046ef738f12d1f934be21e7d1fe7c71e727a635802fc20048d8f74ad773b59},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26847. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI coding agents now author a large share of pull requests (PRs) merged into popular open-source projects. A merged agent PR is usually considered finished work; yet, prior studies have reported issues in agent code after the merge (e.g., code smells and static-analysis issues). However, little is known about how often a merged agent PR is fixed afterward, and who actually authors the fixing. In this paper, we follow 6,774 merged agent PRs across five AI coding agents (OpenAI Codex, GitHub Copilot, Devin, Cursor, and Claude Code) from the AIDev-pop dataset (open-source repositories with at least 500 stars) into their follow-up fixes, against a baseline of 5,044 contemporaneous human PRs from the same repositories. We link each merge to its candidate fixes, verify every candidate with human annotators and an LLM judge that matches human-level agreement (binary Cohen's Kappa=0.78 against a human-human K=0.77, Direct-fix precision 90%), and attribute the fixing work at the PR and the commit level. Our findings show that (1) merged agent PRs attract verified fixes at 1.62 times the odds of merged human PRs in the same repositories over the same period of time; (2) 69.6% of verified fixes in agent merges come from the same agent; and (3) 76.4% of the verified fix PRs are agent-authored throughout all commits. These results show that agents currently largely finish their own job, but their merges still require fixing more often than human merges.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-24 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.26847 — 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 2026-10-08T10:13:35.103Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).