研究显示简单 LLM harness 在微服务根因分析上胜过手工编排智能体
Free to Look, Free to Reason: Simple LLM Harnesses Outdiagnose Hand-Crafted Root Cause Analysis Agents
AI 导读
arXiv 论文 arXiv:2610.35767 比较 three 个不做流程约束的简单 harness（单次调用证据包、SQL 智能体、Codex 编码智能体）与 five 个已发表 LLM RCA 智能体及非 LLM 方法，在 RCAtlas 90 个案例上评估，覆盖六模型和三档推理力度。
正文 · 原文
Abstract: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.
| Comments: | 12 pages |
| Subjects: | Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Software Engineering (cs.SE) |
| Cite as: | arXiv:2610.35767 [cs.AI] |
| (or arXiv:2610.35767v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35767 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Tingzhu Bi [view email]
[v1]
Mon, 26 Oct 2026 17:12:02 UTC (303 KB)
来源：arXiv cs.AI · arxiv.org