Metraipolis › archive › dc_ec55c294d352

Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files — arXiv:2610.21073

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.21073
License (as archived)
CC0-1.0
Archived
2026-10-16T10:25:26.477Z
SHA-256 of the archived text
5c5e952afa23d552cfb03f3f6d75af8ff4aa2ec432857a03bee521f545f4341e
Stable URL of this page
https://metraipolis.com/documento/dc_ec55c294d352

How to cite

Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files — arXiv:2610.21073 — arXiv (en), https://arxiv.org/abs/2610.21073 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec55c294d352 (Metraipolis archive dc_ec55c294d352, sha256 5c5e952afa23d552cfb03f3f6d75af8ff4aa2ec432857a03bee521f545f4341e)
BibTeX
@misc{dcec55c294d352,
  title = {Skip the Compressor: Coding Agents Fix More Issues When They Pick Whole Files — arXiv:2610.21073},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.21073},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec55c294d352; sha256 5c5e952afa23d552cfb03f3f6d75af8ff4aa2ec432857a03bee521f545f4341e},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.21073. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

A coding agent works on repositories that can be far larger than its context window can hold. Prompt compressors and retrievers offer solutions to this problem, but patching an issue needs two things at once: the files that must change, and their code exactly as written, since the model must reproduce the lines it edits. Retrievers rank code by its similarity to the issue rather than by whether it must change, and compressors delete text to fit the budget. We show that at an equal token budget, an agent resolves more issues when the budget goes to choosing which files to show verbatim, as our simple selector CQ2-CARE does, than when it goes to pruning tokens or retrieving chunks. We fit every context to the same per-issue budget on 300 recent SWE-rebench issues and grade each patch with the benchmark's tests. With GPT-5.6 and Claude Opus 5, CQ2-CARE resolves 43.7% and 46.7% of the issues, 6.3 points more than the best of three compressors with either model, and 9.3 and 12.7 points more than the best of three retrievers. CQ2-CARE even resolves more issues than two methods trained for issue resolution, SweRank (by 0.7 and 1.7 points) and SWE-Pruner (by 2.0 and 7.3). Our analysis shows the defects of the baseline methods: retrievers often miss the files to edit, and compressors keep them but alter their text, so fewer patches apply. Exact-file selection needs no compression model and shows every line as the repository has it, so the model can quote the code it edits.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2610.21073 — 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 2026-10-16T08:48:17.693Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).