mlsanityData to 7 Oct 2026

PRAXIS: Integrating Program Analysis with Observability for Root-Cause Analysis

arXiv 2512.22113 ↗First posted 26 Dec 2025cs.DC cs.AI cs.SEcited by 2

Not on the map. Why?

Abstract (arXiv)

Unresolved production cloud incidents cost an average of over 2M per hour. This paper introduces PRAXIS, an orchestrator that manages and deploys an agentic workflow for diagnosing code- and configuration-caused cloud incidents. PRAXIS employs an LLM-driven structured traversal over two types of graph: (1) a service dependency graph (SDG) that captures microservice-level dependencies; and (2) a hammock-block program dependence graph (PDG) that captures code-level dependencies for each microservice. Compared to state-of-the-art ReAct baselines, PRAXIS improves RCA accuracy by up to 6.3x while reducing token consumption by 5.3x. PRAXIS is demonstrated on a set of 30 comprehensive real-world incidents that is being compiled into an RCA benchmark.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 28 of its 82 references that are in the map. First posted on arXiv 26 Dec 2025.

Builds on

28 of 82 references.

References · 28

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  3. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  4. 2019Time-Series Anomaly Detection Service at Microsoftcited by 163
  5. 2024Graph Chain-of-Thought: Augmenting Large Language Models by Reasoning on Graphscited by 116
  6. 2023Automatic Root Cause Analysis via Large Language Models for Cloud Incidentscited by 82
  7. 2025LocAgent: Graph-Guided LLM Agents for Code Localizationcited by 82
  8. 2024Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphscited by 77
  9. 2023RCAgent: Cloud Root Cause Analysis by Autonomous Agents with Tool-Augmented Large Language Modelscited by 62
  10. 2024Exploring LLM-based Agents for Root Cause Analysiscited by 60
  11. 2025ITBench: Evaluating AI Agents across Diverse Real-World IT Automation Taskscited by 48
  12. 2024Paths-over-Graph: Knowledge Graph Empowered Large Language Model Reasoningcited by 44
16 more
  1. 2023Recommending Root-Cause and Mitigation Steps for Cloud Incidents using Large Language Modelscited by 38
  2. 2025AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Cloudscited by 36
  3. 2025Flow-of-Action: SOP Enhanced LLM-Based Multi-Agent System for Root Cause Analysiscited by 32
  4. 2021CloudRCA: A Root Cause Analysis Framework for Cloud Computing Platformscited by 24
  5. 2025Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunitiescited by 23
  6. 2023Xpert: Empowering Incident Management with Query Recommendations via Large Language Modelscited by 22
  7. 2024X-lifecycle Learning for Cloud Incident Management using LLMscited by 19
  8. 2025STRATUS: A Multi-agent System for Autonomous Reliability Engineering of Modern Cloudscited by 18
  9. 2023Assess and Summarize: Improve Outage Understanding with Large Language Modelscited by 17
  10. 2025Butterfly Effects in Toolchains: A Comprehensive Analysis of Failed Parameter Filling in LLM Tool-Agent Systemscited by 17
  11. 2024Root Cause Analysis for Microservice System based on Causal Inference: How Far Are We?cited by 14
  12. 2025COCA: Generative Root Cause Analysis for Distributed Systems with Code Knowledgecited by 10
  13. 2024Mutiny! How does Kubernetes fail, and what can we do about it?cited by 3
  14. 2025An Empirical Study of Production Incidents in Generative AI Cloud Servicescited by 3
  15. 2024Codellm-Devkit: A Framework for Contextualizing Code LLMs with Program Analysis Insightscited by 2
  16. 2025ErrorPrism: Reconstructing Error Propagation Paths in Cloud Service Systemscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagationcited by 3
  2. 2026Auditable Graph-Guided Root Cause Analysis for Kubernetes Incidentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Cloud-OpsBench: A Reproducible Benchmark for Agentic Root Cause Analysis in Cloud Systems
  2. 2026Graphical Causal Reasoning for Root Cause Analysis in Cloud Networks
  3. 2026GALA: Graph-Augmented LLM Agents for Root Cause Analysis and Incident Response in Microservices
  4. 2026Stalled, Biased, and Confused: Uncovering Reasoning Failures in LLMs for Cloud-Based Root Cause Analysis
  5. 2026STAR: A Stage-attributed Triage and Repair framework for RCA Agents in Microservices
  6. 2024Cloud Atlas: Efficient Fault Localization for Cloud Systems using Language Models and Causal Insight
  7. 2025GALA: Can Graph-Augmented Large Language Model Agentic Workflows Elevate Root Cause Analysis?
  8. 2026How Far Can Root Cause Analysis Go on Real-World Telemetry Data?