Metraipolis › archive › dc_995d34690ecc
Runnable Commit Untangling for Coding Agents — arXiv:2610.11593
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11593
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:00:15.588Z
- SHA-256 of the archived text
a749c6ab5aace33c9302a5226c1666b44bf2b5d30f5813a20ca9698c9e44269e- Stable URL of this page
https://metraipolis.com/documento/dc_995d34690ecc
How to cite
Runnable Commit Untangling for Coding Agents — arXiv:2610.11593 — arXiv (en), https://arxiv.org/abs/2610.11593 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_995d34690ecc (Metraipolis archive dc_995d34690ecc, sha256 a749c6ab5aace33c9302a5226c1666b44bf2b5d30f5813a20ca9698c9e44269e)
BibTeX
@misc{dc995d34690ecc,
title = {Runnable Commit Untangling for Coding Agents — arXiv:2610.11593},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11593},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_995d34690ecc; sha256 a749c6ab5aace33c9302a5226c1666b44bf2b5d30f5813a20ca9698c9e44269e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11593. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Coding agents produce large, tangled patches that mix multiple development purposes, making the code hard to review and maintain. Commit untangling offers the promise of organizing such large patches into untangled, manageable commits. This paper emphasizes two important limitations in existing commit untangling studies. First, they do not consider that untangled commits are ordered and should leave the code runnable. In practice, maintainers are unlikely to accept commits that prevent the code from running. Second, existing studies claim that commit untangling helps software maintenance. However, they conduct syntactic comparisons between the untangled commits and developers' original commits without directly showing the claimed maintenance benefits. To address these gaps, this paper makes two novel contributions: (1) RucTangle, the first agentic method that untangles commits while keeping the code runnable after each commit; and (2) TangleEval, the first evaluation framework that quantifies how untangled, manageable commit histories help coding agents repair bugs. We compare RucTangle against four untangling methods on 131 agent-generated patches. All histories produced by RucTangle are runnable, while baselines produce 20.6%-37.4% unrunnable commit histories. We further collect 453 agent-generated patches that introduce regressions (i.e., causing previously passing tests to fail) and ask two other coding agents to repair regressions. Augmenting agent context with RucTangle-produced histories yields 5.2% absolute improvement in pass@1. We also analyze agent trajectories to learn how they use untangled commits to navigate and fix bugs. Our findings demonstrate the value of adopting established software engineering practices in the era of coding agents, which broaden the future research agenda: how can agents actively use software history to make better development decisions? Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.11593 — 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 2026-10-09T05:47:01.792Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).