Metraipolis › archive › dc_de31aa4d5df4
Free to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis Agents — arXiv:2610.35767
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.35767
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-27T07:59:12.313Z
- SHA-256 of the archived text
690505f5a55b06fae448a2735363ab47c16daab75dabaaad130025cb9a47307f- Stable URL of this page
https://metraipolis.com/documento/dc_de31aa4d5df4
How to cite
Free to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis Agents — arXiv:2610.35767 — arXiv (en), https://arxiv.org/abs/2610.35767 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de31aa4d5df4 (Metraipolis archive dc_de31aa4d5df4, sha256 690505f5a55b06fae448a2735363ab47c16daab75dabaaad130025cb9a47307f)
BibTeX
@misc{dcde31aa4d5df4,
title = {Free to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis Agents — arXiv:2610.35767},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.35767},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de31aa4d5df4; sha256 690505f5a55b06fae448a2735363ab47c16daab75dabaaad130025cb9a47307f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.35767. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Root cause analysis (RCA) of microservice failures has attracted many LLM agents whose investigation is hand-crafted, through standard operating procedures, fixed stages and role agents. Each is evaluated on its own data against few baselines, so it is unknown whether this design beats letting a capable model investigate on its own. We compare three simple harnesses that prescribe none of the model's calls (one call over an evidence package, a SQL agent and the Codex coding agent) with five published LLM RCA agents and with statistical and causal methods on RCAtlas, 90 validated cases from eight public datasets, across six models and three reasoning efforts. The simple harnesses are the most accurate (PR@1 65-77% on three mid-tier models), ahead of the published agents (16-53%) and the non-LLM methods (6-39%), on every model on which both families were run. The published agents fix from a tenth to all of their model calls in the program, and a case study shows how these prescriptions skip the decisive evidence. A stronger model mainly improves reliability, a multi-turn harness mainly improves aptitude, and more reasoning effort changes accuracy by a few points at most while multiplying the time by up to seven. Among runs more accurate than the best non-LLM method, every Pareto-optimal run in cost or time uses a simple harness. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Distributed, Parallel, and Cluster Computing (cs.DC); Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2610.35767 — 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 2026-10-27T07:55:30.769Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).