SADE: Symptom-Aware Diagnostic Escalation for LLM-Based Network Troubleshooting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911652201365504 |
|---|---|
| author | Tseng, Kuan-Hao Bogahawatta, Niruth Ginige, Yasod Dekic, Kosta Sivanathan, Arunan Seneviratne, Suranga |
| author_facet | Tseng, Kuan-Hao Bogahawatta, Niruth Ginige, Yasod Dekic, Kosta Sivanathan, Arunan Seneviratne, Suranga |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_04530 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SADE: Symptom-Aware Diagnostic Escalation for LLM-Based Network Troubleshooting Tseng, Kuan-Hao Bogahawatta, Niruth Ginige, Yasod Dekic, Kosta Sivanathan, Arunan Seneviratne, Suranga Networking and Internet Architecture Artificial Intelligence 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. |
| title | SADE: Symptom-Aware Diagnostic Escalation for LLM-Based Network Troubleshooting |
| topic | Networking and Internet Architecture Artificial Intelligence |
| url | https://arxiv.org/abs/2605.04530 |