Metraipolis › archive › dc_35c49a5dae65

Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework — arXiv:2608.08950

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08950
License (as archived)
CC0-1.0
Archived
2026-10-19T09:00:57.260Z
SHA-256 of the archived text
8911d0d708ef74e63d728f88a32f8bf3fa0eca87c302378e223aba3341112dd2
Stable URL of this page
https://metraipolis.com/documento/dc_35c49a5dae65

How to cite

Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework — arXiv:2608.08950 — arXiv (en), https://arxiv.org/abs/2608.08950 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_35c49a5dae65 (Metraipolis archive dc_35c49a5dae65, sha256 8911d0d708ef74e63d728f88a32f8bf3fa0eca87c302378e223aba3341112dd2)
BibTeX
@misc{dc35c49a5dae65,
  title = {Independent Patch Verification for Coding Agents with a Bidirectional Reconstruct-and-Verify Framework — arXiv:2608.08950},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08950},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_35c49a5dae65; sha256 8911d0d708ef74e63d728f88a32f8bf3fa0eca87c302378e223aba3341112dd2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08950. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Autonomous coding agents powered by large language models can now generate code patches directly from bug reports, but a fundamental gap remains: once a patch is produced, no mechanism independently verifies whether it truly resolves the reported problem. Prior work has sought to address this through iterative self-refinement and inference-time scaling, but these approaches either review the patch under the same interpretation that produced it or broaden candidate generation without verifying individual patches, and neither provides an explicit verification signal for assessing patch correctness. We propose RETRACE, a training-free post-generation verification framework that derives such a signal through bidirectional reconstruction and reconciliation. When a coding agent generates a candidate patch for an issue, RETRACE performs forward reconstruction to build an explicit repair rationale from the issue and the agent's trajectory; backward reconstruction then independently infers, from the patch and its trajectory alone and without access to the original issue, a description of the problem the patch appears to address, and compares this reconstruction against the original issue to produce an alignment verdict; a reconciliation stage then checks the consistency between the forward rationale and the patch, diagnoses the source of any misalignment, and either submits the patch or produces targeted revision guidance. Evaluated on SWE-bench Verified with two backbones (GPT-5-mini and MiniMax-2.5), RETRACE lifts Pass@1 by 7.0% and 3.6% respectively on the mini-SWE-agent scaffold, and delivers comparable gains on OpenHands without modification. Ablation experiments show that both the forward and backward stages contribute to the overall improvement and that adding reconciliation yields further gains.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-08-11 in cs.SE).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2608.08950 — 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 2026-10-19T09:00:31.488Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).