mlsanityData to 7 Oct 2026

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

arXiv 2605.04530 ↗First posted 6 May 2026cs.NI cs.AIcited by 3

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 14 of its 35 references that are in the map. First posted on arXiv 6 May 2026.

Builds on

14 of 35 references.

References · 14

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  3. 2023Automatic Root Cause Analysis via Large Language Models for Cloud Incidentscited by 82
  4. 2024NetLLM: Adapting Large Language Models for Networkingcited by 76
  5. 2023RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Modelscited by 62
  6. 2024Exploring LLM-based Agents for Root Cause Analysiscited by 60
  7. 2023Large Language Models for Networking: Applications, Enabling Techniques, and Challengescited by 28
  8. 2024A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directionscited by 25
  9. 2024Can LLMs Understand Computer Networks? Towards a Virtual System Administratorcited by 11
  10. 2024Large Language Models for Zero Touch Network Configuration Managementcited by 9
  11. 2025A Network Arena for Benchmarking AI Agents on Network Troubleshootingcited by 8
  12. 2024GeNet: A Multimodal LLM-Based Co-Pilot for Network Topology and Configurationcited by 6
2 more
  1. 2024Mobile Network Configuration Recommendation using Deep Generative Graph Neural Networkcited by 3
  2. 2025Towards a Playground to Democratize Experimentation and Benchmarking of AI Agents for Network Troubleshootingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026Let AI Agents Translate Networks, Not Reason About Themcited by 0
  2. 2026FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Ticketscited by 0
  3. 2026What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Large Language Models (LLMs) for Telecom Root Cause Analysis (RCA): A Structured Reasoning Framework for Evidence-Grounded Diagnosis
  2. 2026SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation
  3. 2026Agentic Diagnostic Reasoning over Telecom and Datacenter Infrastructure
  4. 2026CUJBench: Benchmarking LLM-Agent on Cross-Modal Failure Diagnosis from Browser to Backend
  5. 2026From Anomalies to Failures: Constructing Causal Error Graphs for Agentic Trace Diagnosis
  6. 2026Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents
  7. 2026DiagChain: A Diagnostic Benchmark for Evaluating LLM Agents on Evidence-Grounded Attack Chain Reconstruction
  8. 2026QoEReasoner: An Agentic Reasoning Framework for Automated and Explainable QoE Diagnosis in RANs