SADE: Symptom-Aware Diagnostic Escalation for LLM-Based Network Troubleshooting

TL;DR

SADE introduces a symptom-aware, layer-by-layer diagnostic policy for LLM-based network troubleshooting, significantly improving root-cause localization accuracy over baseline methods.

Contribution

It encodes classical troubleshooting methodology into an explicit policy, enhancing LLM agents' effectiveness in network fault diagnosis.

Findings

SADE improves root-cause F1 by 37 percentage points over baseline.

The diagnostic policy accounts for 22 of those points, independent of model upgrades.

SADE outperforms existing approaches on the NIKA benchmark.

Abstract

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.