mlsanityData to 7 Oct 2026

Automatic Root Cause Analysis via Large Language Models for Cloud Incidents

arXiv 2305.15778 ↗First posted 25 May 2023cs.SEcited by 82

Not on the map. Why?

Cited by 25 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Ensuring the reliability and availability of cloud services necessitates efficient root cause analysis (RCA) for cloud incidents. Traditional RCA methods, which rely on manual investigations of data sources such as logs and traces, are often laborious, error-prone, and challenging for on-call engineers. In this paper, we introduce RCACopilot, an innovative on-call system empowered by the large language model for automating RCA of cloud incidents. RCACopilot matches incoming incidents to corresponding incident handlers based on their alert types, aggregates the critical runtime diagnostic information, predicts the incident's root cause category, and provides an explanatory narrative. We evaluate RCACopilot using a real-world dataset consisting of a year's worth of incidents from Microsoft. Our evaluation demonstrates that RCACopilot achieves RCA accuracy up to 0.766. Furthermore, the diagnostic information collection component of RCACopilot has been successfully in use at Microsoft for over four years.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 May 2023.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 2; 2024: 22; 2025: 18; 2026: 40.

82 papers.

Sort:

By area:

  1. 2023Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generationcited by 73
  2. 2024MarsCode Agent: AI-native Automated Bug Fixingcited by 68
  3. 2024Large Language Models for Cyber Security: A Systematic Literature Reviewcited by 65
  4. 2023RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Modelscited by 62
  5. 2026SkillForge: Forging Domain-Specific, Self-Evolving Agent Skills in Cloud Technical Supportcited by 43
  6. 2025AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Cloudscited by 36
  7. 2025Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysiscited by 32
  8. 2024Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4cited by 28
  9. 2024mABC: multi-Agent Blockchain-Inspired Collaboration for root cause analysis in micro-services architecturecited by 26
  10. 2024CE-CoLLM: Efficient and Adaptive Large Language Models Through Cloud-Edge Collaborationcited by 25
  11. 2024A Survey on Large Language Models for Communication, Network, and Service Management: Application Insights, Challenges, and Future Directionscited by 25
  12. 2024An Empirical Study on LLM-based Agents for Automated Bug Fixingcited by 23
38 more
  1. 2024Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspectivecited by 22
  2. 2024X-lifecycle Learning for Cloud Incident Management using LLMscited by 19
  3. 2024Building AI Agents for Autonomous Clouds: Challenges and Design Principlescited by 19
  4. 2025A Survey of AIOps in the Era of Large Language Modelscited by 18
  5. 2024Face It Yourselves: An LLM-Based Two-Stage Strategy to Localize Configuration Errors via Logscited by 17
  6. 2024LogLM: From Task-based to Instruction-based Automated Log Analysiscited by 13
  7. 2025TAMO: Fine-Grained Root Cause Analysis via Tool-Assisted LLM Agent with Multi-Modality Observation Data in Cloud-Native Systemscited by 13
  8. 2026Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systemscited by 13
  9. 2025Adaptive Root Cause Localization for Microservice Systems with Multi-Agent Recursion-of-Thoughtcited by 11
  10. 2024A Comprehensive Survey on Root Cause Analysis in (Micro) Services: Methodologies, Challenges, and Trendscited by 10
  11. 2024LEMMA-RCA: A Large Multi-modal Multi-domain Dataset for Root Cause Analysiscited by 9
  12. 2025Cloud Infrastructure Management in the Age of AI Agentscited by 9
  13. 2025Large Language Models for Security Operations Centers: A Comprehensive Surveycited by 9
  14. 2025NetArena: Dynamic Benchmarks for AI Agents in Network Automationcited by 8
  15. 2026Agentic Memory Enhanced Recursive Reasoning for Root Cause Localization in Microservicescited by 8
  16. 2026SREGym: A Live Benchmark for AI SRE Agents with High-Fidelity Failure Scenarioscited by 8
  17. 2024Adapting Large Language Models to Log Analysis with Interpretable Domain Knowledgecited by 6
  18. 2025The Multi-Agent Fault Localization System Based on Monte Carlo Tree Search Approachcited by 6
  19. 2025StepFly: Agentic Troubleshooting Guide Automation for Incident Diagnosiscited by 5
  20. 2024Knowledge-aware Alert Aggregation in Large-scale Cloud Systems: a Hybrid Approachcited by 4
  21. 2024The Vision of Autonomic Computing: Can LLMs Make It a Reality?cited by 4
  22. 2025AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Modelcited by 4
  23. 2025A Cost-Effective Near-Storage Processing Solution for Offline Inference of Long-Context LLMscited by 4
  24. 2025Simplifying Root Cause Analysis in Kubernetes with StateGraph and LLMcited by 4
  25. 2026Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agentscited by 4
  26. 2024No Size Fits All: The Perils and Pitfalls of Leveraging LLMs Vary with Company Sizecited by 3
  27. 2025ProRCA: A Causal Python Package for Actionable Root Cause Analysis in Real-world Business Scenarioscited by 3
  28. 2026Graph-Free Root Cause Analysiscited by 3
  29. 2026E2E-REME: Towards End-to-End Microservices Auto-Remediation via Experience-Simulation Reinforcement Fine-Tuningcited by 3
  30. 2026SADE: Symptom-Aware Diagnostic Escalation for LLM-Based Network Troubleshootingcited by 3
  31. 2024FaultProfIT: Hierarchical Fault Profiling of Incident Tickets in Large-scale Cloud Systemscited by 2
  32. 2024Dependency Aware Incident Linking in Large Cloud Systemscited by 2
  33. 2024Generative transformations and patterns in LLM-native approaches for software verification and falsificationcited by 2
  34. 2025FAA Framework: A Large Language Model-Based Approach for Credit Card Fraud Investigationscited by 2
  35. 2025PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysiscited by 2
  36. 2026TxRay: Agentic Postmortem of Live Blockchain Attackscited by 2
  37. 2026NeSy-Edge: Neuro-Symbolic Trustworthy Self-Healing in the Computing Continuumcited by 2
  38. 2026Towards Robust LLM Post-Training: Automatic Failure Management for Reinforcement Fine-Tuningcited by 2

50 most cited of 82 All 82 (JSON)