Metraipolis › archive › dc_7258c6089c99
Cost-Effective Repository Exploration for Agentic Issue Localization — arXiv:2608.29675
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.29675
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T07:52:12.213Z
- SHA-256 of the archived text
8a7816467ba7f0608eb388dd75f7a2f45859bcf7a8932dc858724fd28c869b1d- Stable URL of this page
https://metraipolis.com/documento/dc_7258c6089c99
How to cite
Cost-Effective Repository Exploration for Agentic Issue Localization — arXiv:2608.29675 — arXiv (en), https://arxiv.org/abs/2608.29675 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7258c6089c99 (Metraipolis archive dc_7258c6089c99, sha256 8a7816467ba7f0608eb388dd75f7a2f45859bcf7a8932dc858724fd28c869b1d)
BibTeX
@misc{dc7258c6089c99,
title = {Cost-Effective Repository Exploration for Agentic Issue Localization — arXiv:2608.29675},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.29675},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7258c6089c99; sha256 8a7816467ba7f0608eb388dd75f7a2f45859bcf7a8932dc858724fd28c869b1d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.29675. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Repository exploration is a distinct and costly stage of coding-agent pipelines: before generating a patch, an agent must identify which repository files are likely to matter. We study whether this stage can be delegated to lower-cost models while retaining useful localization quality. Using our IssueLoc-Bench, we evaluate five explorer models under the same read-only interactive interface on 499 SWE-bench Verified-derived tasks and 500 tasks from 153 additional repositories. We measure early candidate discovery, top-three gold-file coverage, strict file-set recovery, agent time, and token usage, with paired instance-level uncertainty and repository-clustered sensitivity analysis. The highest-quality explorer leads across localization metrics, but substantially cheaper operating points emerge: depending on the model and evaluation arm, lower-cost explorers retain approximately 78-94% of the reference Hit@3 and 73-92% of its F1 while reducing mean agent time by 41-88% and token usage by 84-95%. The preferred operating point depends on how localization is consumed downstream: ranking and coverage metrics characterize recoverable candidate handoffs, whereas F1 and exact match characterize restrictive file gates. These results support treating repository exploration as an independently measurable and budgetable stage of modular coding agents, with explorer selection guided by the downstream handoff contract. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.29675 — 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 2026-10-17T07:28:26.791Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).