mlsanityData to 7 Oct 2026

AgentOps: Enabling Observability of LLM Agents

arXiv 2411.05285 ↗First posted 8 Nov 2024cs.AI cs.SEcited by 46

On the map: LLM agents and tool use → Software engineering coding agents

Abstract (arXiv)

Large language model (LLM) agents have demonstrated remarkable capabilities across various domains, gaining extensive attention from academia and industry. However, these agents raise significant concerns on AI safety due to their autonomous and non-deterministic behavior, as well as continuous evolving nature . From a DevOps perspective, enabling observability in agents is necessary to ensuring AI safety, as stakeholders can gain insights into the agents' inner workings, allowing them to proactively understand the agents, detect anomalies, and prevent potential failures. Therefore, in this paper, we present a comprehensive taxonomy of AgentOps, identifying the artifacts and associated data that should be traced throughout the entire lifecycle of agents to achieve effective observability. The taxonomy is developed based on a systematic mapping study of existing AgentOps tools. Our taxonomy serves as a reference template for developers to design and implement AgentOps infrastructure that supports monitoring, logging, and analytics. thereby ensuring AI safety.

Key facts. Cited by 46 papers in the map (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 6 of its 8 references that are in the map. First posted on arXiv 8 Nov 2024.

Builds on

6 of 8 references.

References · 6

  1. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  2. 2024Visibility into AI Agentscited by 77
  3. 2017Guidelines for including grey literature and conducting multivocal literature reviews in software engineeringcited by 38
  4. 2024Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agentscited by 35
  5. 2023Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model based Agentscited by 13
  6. 2024Swiss Cheese Model for AI Safety: A Taxonomy and Reference Architecture for Multi-Layered Guardrails of Foundation Model Based Agentscited by 13

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 8; 2026: 37.

46 papers.

Sort:

By area:

  1. 2026From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agentscited by 29
  2. 2025AgentSight: System-Level Observability for AI Agents Using eBPFcited by 18
  3. 2026Auditable Agentscited by 14
  4. 2026Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causescited by 11
  5. 2026The Evolution of Tool Use in LLM Agents: From Single-Tool Call to Multi-Tool Orchestrationcited by 11
  6. 2026TrajAudit: Automated Failure Diagnosis for Agentic Coding Systemscited by 11
  7. 2024Evaluation-Driven Development and Operations of LLM Agents: A Process Model and Reference Architecturecited by 10
  8. 2026AgentTrace: A Structured Logging Framework for Agent System Observabilitycited by 8
  9. 2025Beyond Task Completion: An Assessment Framework for Evaluating Agentic AI Systemscited by 7
  10. 2026FlowSteer: Prompt-Only Workflow Steering Exposes Planning-Time Vulnerabilities in Multi-Agent LLM Systemscited by 7
  11. 2026REFLECT: Intervention-Supported Error Attribution for Silent Failures in LLM Agent Tracescited by 7
  12. 2026AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agentscited by 7
34 more
  1. 2025Oversight Structures for Agentic AI in Public-Sector Organizationscited by 6
  2. 2025Agentic Services Computingcited by 6
  3. 2025RAGOps: Operating and Managing Retrieval-Augmented Generation Pipelinescited by 5
  4. 2025LumiMAS: A Comprehensive Framework for Real-Time Monitoring and Enhanced Observability in Multi-Agent Systemscited by 4
  5. 2026ClawTrace: Cost-Aware Tracing for LLM Agent Skill Distillationcited by 4
  6. 2026Towards Security-Auditable LLM Agents: A Unified Graph Representationcited by 4
  7. 2026GRADE: Graph Representation of LLM Agent Dependency and Executioncited by 4
  8. 2026The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculuscited by 3
  9. 2026Clawed and Dangerous: Can We Trust Open Agentic Systems?cited by 3
  10. 2026AI Agents Push Humans Out of the Loopcited by 3
  11. 2026Repair or Resample? Rethinking Failure Debugging in LLM Multi-Agent Systemscited by 3
  12. 2026Designing for Doubt: The Case for Informed Abstention in Autonomous Agentscited by 2
  13. 2026Agentic Configuration Management (ACM): A Reference Configuration Model for Governed Agentic Systemscited by 2
  14. 2025OpenDerisk: An Industrial Framework for AI-Driven SRE, with Design, Implementation, and Case Studiescited by 1
  15. 2025HarmTransform: Transforming Explicit Harmful Queries into Stealthy via Multi-Agent Debatecited by 1
  16. 2026Anonymous-by-Construction: An LLM-Driven Framework for Privacy-Preserving Textcited by 1
  17. 2026Harnessing Agent Skills: Architectural Patterns and a Reference Architecture for Skill-Mediated LLM Agentscited by 1
  18. 2026How Do Practitioners Build SE Agents? Insights from a Mixed-Methods Studycited by 1
  19. 2026Blockchain Empowered Trustworthy Agent Networks: Foundations, Taxonomy, and Future Directionscited by 1
  20. 2026TelemetrySuffBench: Is Agent Telemetry Sufficient for Failure-Origin Diagnosis?cited by 1
  21. 2026Observability and Fault Injection for LLM-Based Multi-Agent Systems in Software Engineeringcited by 1
  22. 2026Agent-Integrated Software: Interaction Contracts and Continuous Assurancecited by 1
  23. 2026Agent System Operations: Categorization, Challenges, and Future Directionscited by 0
  24. 2026Agent Behavior Mining: Generative AI Agent Governance in Business Processescited by 0
  25. 2026Cross-Agent Campaign Attribution: Linking Asynchronous Attacks Across LLM Agentscited by 0
  26. 2026Toward Continuous Assurance for the Democratization of AI Agent Creation in Industrycited by 0
  27. 2026The CASE Framework: A Multi-Disciplinary Control Architecture for Governing Enterprise Agentic AIcited by 0
  28. 2026AUDITA: certified auditing and causal attribution of adverse outcomes in autonomous multi-agent systemscited by 0
  29. 2026Towards Agentic Cloud Engineering: Graph and Loop Engineering with a Zero-Trust Agent Harnesscited by 0
  30. 2026AgentKernel: The Trust-Native Agentic Operating Systemcited by 0
  31. 2026Who Holds the Pen? Let Specifications, Not Agents, Sign Offcited by 0
  32. 2026AgentWare: Automating the Lifecycle of Agentic Applications across the Edge-to-Cloud Continuumcited by 0
  33. 2026Trustworthy Data- and ML-Ops for Intelligent Transportation Systems and Logisticscited by 0
  34. 2026Verify Claims, Not Scores: Evidence-Based Verification of Modular Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on AgentOps: Categorization, Challenges, and Future Directions
  2. 2025Taming Uncertainty via Automation: Observing, Analyzing, and Optimizing Agentic AI Systems
  3. 2026Large Language Models for Agentic NetOps and AIOps: Architectures, Evaluation, and Safety
  4. 2025Agentic AI Process Observability: Discovering Behavioral Variability
  5. 2025Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agents
  6. 2026LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment
  7. 2024Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents
  8. 2026Towards Verifiably Safe Tool Use for LLM Agents