Problem
Research questions and friction points this paper is trying to address.
Automated Root Cause Analysis
Large Language Models
External Harness
Self-Evolving
Diagnosis Accuracy
From General Agents to RCA Experts: A Self-Evolving Harness for Root Cause Analysis
🤖 AI Summary
研究通过构建自我进化的OpsHarness框架，利用大型语言模型的通用能力改进根因分析准确性，解决现有方法精度不足的问题。
📝 Abstract
Automated root cause analysis (RCA) with large language models (LLMs) has drawn growing attention. Today, SREs typically automate RCA with LLMs in one of two ways: directly using a general-purpose agent (e.g., Codex or Claude Code) for diagnosis, or building a specialized RCA agent from scratch. As mainstream general agents grow more capable and iterate quickly, our quantitative study finds that the former now often surpasses the latter. Its accuracy, however, still falls short of production needs, and this gap stems mainly from the external adaptation layer outside the agent's general capabilities, namely the harness. We therefore argue that LLM-based RCA should focus on this external harness, reusing the strong general capabilities of a modern agent rather than rebuilding an agent from scratch. A key capability of such a harness is to self-evolve, accumulating system-specific experience from past diagnoses so that it gets better the more it is used. We introduce OpsHarness, a self-evolving RCA harness that turns diagnosis experience into reusable expertise. Its data plane combines layered operational knowledge with an idea-card tool library, while its control plane coordinates setup, diagnosis, evolution, and verification. During evolution, OpsHarness contrasts successful and failed trajectories, converts their evidence into atomic proposals, and admits updates only through a dual-gate verification process designed to prevent overfitting and regression. Across two public benchmarks and an industrial deployment, OpsHarness achieves 59.0\% top-1 accuracy, improving over a bare general agent by 63.4\% and over baseline RCA agents by 4.02$\times$.
Innovation
Methods, ideas, or system contributions that make the work stand out.
self-evolving
RCA harness
external adaptation layer
general-purpose agent
dual-gate verification
🔎 Similar Papers
No similar papers found.
