让大模型按工程师思路分步排查网络故障，准确率提升37个百分点。
SADE: Symptom-Aware Diagnostic Escalation for LLM-Based Network Troubleshooting
- 设计分阶段诊断流程，先收集证据再提出假设，避免思维混乱。
- 在523个未见故障场景中，根因定位准确率比基线高37个百分点。
- 适合需要高可靠性的网络运维系统，或想改进AI诊断逻辑的研究者。
大型语言模型（LLM）代理被越来越多地用于网络故障排查，但在公开基准上的根本原因定位性能仍远低于实际部署要求。我们认为这是因为现有代理未体现人类网络工程师所采用的结构化、分层排查方法，而是依赖自由发挥的推理，导致证据收集与假设确认混在一起。本文提出SADE（症状感知的诊断升级机制），将经典的思科故障排查方法转化为显式策略。SADE结合阶段约束的诊断流程（分离证据获取与假设提交），并搭配路由型故障类别技能库和高价值诊断辅助工具。在涵盖11种未见场景的公开NIKA基准上，对523个故障实例进行测试，相比ReAct + GPT-5基线，根因定位F1值提升37个百分点；在相同Claude Sonnet后端下，仅使用SADE策略即带来22个百分点的提升，证明性能增益主要源于诊断策略本身，而非模型升级。
原文摘要 · Abstract (English)
Large language model (LLM) agents are increasingly applied to network troubleshooting, but root-cause localization on public benchmarks remains well below practical deployment thresholds. We argue this is because existing agents do not encode the disciplined, layer-by-layer methodology that human network engineers use, and instead rely on free-form deliberation that conflates evidence acquisition with hypothesis commitment. We present SADE (Symptom-Aware Diagnostic Escalation), an agent that encodes the classical Cisco troubleshooting methodology as an explicit policy. SADE pairs a phase-gated diagnostic workflow, which separates evidence acquisition from hypothesis commitment, with a routed library of fault-family skills and high-yield diagnostic helpers. On a held-out 523 incident set of the public NIKA benchmark covering eleven unseen scenarios, SADE improves root-cause F1 by 37 percentage points over a ReAct + GPT-5 baseline; a model-controlled comparison against the same Claude Sonnet backend without the SADE policy attributes 22 of those points to the diagnostic policy alone, showing that the gain is not a side-effect of the model upgrade.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。