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

arXiv: https://arxiv.org/abs/2605.04530 · HTML: https://mlsanity.com/paper/2605.04530/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 35 references that are in the map.
- First posted on arXiv 6 May 2026.

## Builds on (most cited first, 14 of 14)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Automatic Root Cause Analysis via Large Language Models for Cloud Incidents](https://mlsanity.com/paper/2305.15778/) (2023)
- [NetLLM: Adapting Large Language Models for Networking](https://mlsanity.com/paper/2402.02338/) (2024)
- [RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Models](https://mlsanity.com/paper/2310.16340/) (2023)
- [Exploring LLM-based Agents for Root Cause Analysis](https://mlsanity.com/paper/2403.04123/) (2024)
- [Large Language Models for Networking: Applications, Enabling Techniques, and Challenges](https://mlsanity.com/paper/2311.17474/) (2023)
- [A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directions](https://mlsanity.com/paper/2412.19823/) (2024)
- [Can LLMs Understand Computer Networks? Towards a Virtual System Administrator](https://mlsanity.com/paper/2404.12689/) (2024)
- [Large Language Models for Zero Touch Network Configuration Management](https://mlsanity.com/paper/2408.13298/) (2024)
- [A Network Arena for Benchmarking AI Agents on Network Troubleshooting](https://mlsanity.com/paper/2512.16381/) (2025)
- [GeNet: A Multimodal LLM-Based Co-Pilot for Network Topology and Configuration](https://mlsanity.com/paper/2407.08249/) (2024)
- [Mobile Network Configuration Recommendation using Deep Generative Graph Neural Network](https://mlsanity.com/paper/2406.04779/) (2024)
- [Towards a Playground to Democratize Experimentation and Benchmarking of AI Agents for Network Troubleshooting](https://mlsanity.com/paper/2507.01997/) (2025)

## Built on by (most cited first, 4 of 4)

- [FaulT-Bench: Towards Benchmarking Network Troubleshooting LLM Agents under Unreliable User Tickets](https://mlsanity.com/paper/2608.27021/) (2026)
- [Let AI Agents Translate Networks, Not Reason About Them](https://mlsanity.com/paper/2607.22947/) (2026)
- [What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agents](https://mlsanity.com/paper/2609.39989/) (2026)
- [SoK: Semantic Decision Engines in Network Control Loops](https://mlsanity.com/paper/2610.06425/) (2026)

## 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.