Metraipolis › archive › dc_f2f2dbfc8f91

Toward Bounding Coding-Agent Autonomy in Software Maintenance: A Pilot Study of Boundary Contracts — arXiv:2611.01265

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01265
License (as archived): CC0-1.0
Archived: 2026-11-03T10:35:47.318Z
SHA-256 of the archived text: 2bca0ddff1b939f76036dea29fc1d49d9df46847e4c28321f477ed603fd2df68
Stable URL of this page: https://metraipolis.com/documento/dc_f2f2dbfc8f91

How to cite

Toward Bounding Coding-Agent Autonomy in Software Maintenance: A Pilot Study of Boundary Contracts — arXiv:2611.01265 — arXiv (en), https://arxiv.org/abs/2611.01265 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f2f2dbfc8f91 (Metraipolis archive dc_f2f2dbfc8f91, sha256 2bca0ddff1b939f76036dea29fc1d49d9df46847e4c28321f477ed603fd2df68)

BibTeX

@misc{dcf2f2dbfc8f91,
  title = {Toward Bounding Coding-Agent Autonomy in Software Maintenance: A Pilot Study of Boundary Contracts — arXiv:2611.01265},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01265},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f2f2dbfc8f91; sha256 2bca0ddff1b939f76036dea29fc1d49d9df46847e4c28321f477ed603fd2df68},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01265. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As coding agents gain greater autonomy to modify software repositories, relevant context alone does not define their operational authority. An artifact may be relevant to a maintenance task while being inappropriate to edit; conversely, another artifact may be required even when it is not explicitly mentioned in the request. We explore Boundary Contracts, a machine-readable abstraction that makes task-specific artifact roles (editable, inspect-only, required, and protected) explicit before repository modification begins. We conduct a pilot study on 40 maintenance tasks from a real enterprise repository, comparing the same Codex-based coding agent with and without Boundary Contract information. The boundary-informed condition improves macro edit-selection F1 from 0.440 to 0.682, required-behavior coverage from 0.429 to 0.673, and the number of strictly acceptable patches from 9 of 40 to 18 of 40. To probe whether these gains are explained only by improved file localization, we additionally analyze 21 tasks in which both conditions modify at least one identical file. Differences remain in edit selectivity and patch outcomes, providing initial evidence that explicit artifact roles may influence maintenance behavior beyond localization alone. This pilot does not establish the general effectiveness of Boundary Contracts. Rather, it provides initial evidence for a broader research question: how should the operational boundaries of coding agents be generated, validated, revised, and ultimately enforced as repository-level maintenance becomes increasingly autonomous?

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/2611.01265 — 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 2026-11-03T10:29:48.757Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).