Metraipolis › archive › dc_b6fda4cb812e
Chronos Enables Code Agents to Reason over Software Evolution — arXiv:2610.11578
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11578
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:13:50.198Z
- SHA-256 of the archived text
933b7ac40f46922aa49c4eb7520c4d6f46436fea530c1d2a42a2d739888a74f3- Stable URL of this page
https://metraipolis.com/documento/dc_b6fda4cb812e
How to cite
Chronos Enables Code Agents to Reason over Software Evolution — arXiv:2610.11578 — arXiv (en), https://arxiv.org/abs/2610.11578 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b6fda4cb812e (Metraipolis archive dc_b6fda4cb812e, sha256 933b7ac40f46922aa49c4eb7520c4d6f46436fea530c1d2a42a2d739888a74f3)
BibTeX
@misc{dcb6fda4cb812e,
title = {Chronos Enables Code Agents to Reason over Software Evolution — arXiv:2610.11578},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11578},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b6fda4cb812e; sha256 933b7ac40f46922aa49c4eb7520c4d6f46436fea530c1d2a42a2d739888a74f3},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11578. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Historical pull requests record the design decisions, compatibility constraints, and implementation patterns behind a codebase's current state. Experience relevant to a new task can span related changes whose descriptions emphasize different concerns. We introduce Chronos, a test-time framework that makes this connected history available to large language model (LLM)-based code agents. Chronos distills merged pull requests into structured experience cards and connects them through a typed graph of code-level, developer-intent, and organizational relations. Semantic search identifies entry cards, and weighted multi-hop expansion retrieves connected changes for selective reading. The same memory guides candidate generation and patch selection: a patch-focused change agent and a validation-strategy agent each develop a patch, and an evolution steward consults history to select between them. On SWE-Bench Verified, the full workflow improves SWE-Agent across all six evaluated LLM backbones, raising the mean resolution rate from 69.2% to 72.9% and reaching 79.8% with MiniMax M2.5. With the same backbone, it raises resolution rates from 48.3% to 51.7% on SWE-Bench Pro and from 41.0% to 43.5% on FEA-Bench Lite. Both experience-guided single-agent variants also outperform the base agent. In a human evaluation on 100 tasks with ten cards retrieved per task, graph-grounded retrieval increases the mean number of useful cards from 1.24 to 2.87 over flat semantic retrieval. These results demonstrate the value of PR relations for retrieving useful repository experience and of the evaluated workflows for applying that experience during patch generation and selection. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.CL, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.11578 — 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 2026-10-09T05:47:15.499Z dalla pagina https://arxiv.org/list/cs.CL/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).