mlsanityData to 7 Oct 2026

Agent System Operations: Categorization, Challenges, and Future Directions

arXiv 2606.01581 ↗First posted 1 Jun 2026cs.MAcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

also in 1 more
Abstract (arXiv)

As the reasoning capabilities of Large Language Models (LLMs) continue to advance, LLM-based agent systems offer advantages in flexibility and interpretability over traditional systems, garnering increasing attention. However, despite the widespread research interest and industrial application of agent systems, these systems, like their traditional counterparts, frequently encounter anomalies. These anomalies lead to instability and insecurity, hindering their further development. Therefore, a comprehensive and systematic approach to the operation and maintenance of agent systems is urgently needed. Unfortunately, current research on the operations of agent systems is sparse. To address this gap, we have undertaken a survey on agent system operations with the aim of establishing a clear framework for the field, defining the challenges, and facilitating further development. Specifically, this paper begins by systematically defining anomalies within agent systems, categorizing them into intra-agent anomalies and inter-agent anomalies. Next, we introduce a novel and comprehensive operational framework for agent systems, dubbed Agent System Operations (AgentOps). We provide detailed definitions and explanations of its four key stages: monitoring, anomaly detection, root cause localization, and resolution.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 88 of its 123 references that are in the map. First posted on arXiv 1 Jun 2026.

Builds on

88 of 123 references.

Closest ancestors · 3

Same direction, newest first

  1. 2026Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation26 Mar
  2. 2025TRAIL: Trace Reasoning and Agentic Issue Localization13 May
  3. 2024Smurfs: Multi-Agent System using Context-Efficient DFSDT for Tool Planning9 May

Other references · 85

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  7. 2021Finetuned Language Models Are Zero-Shot Learnerscited by 3,747
  8. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,383
  9. 2023Self-Refine: Iterative Refinement with Self-Feedbackcited by 3,317
  10. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,155
  11. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  12. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,906
38 more
  1. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  2. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  3. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineeringcited by 1,628
  4. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,371
  5. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  6. 2022WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agentscited by 1,197
  7. 2020ALFWorld: Aligning Text and Embodied Environments for Interactive Learningcited by 1,143
  8. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  9. 2023Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generationcited by 795
  10. 2023SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Modelscited by 787
  11. 2023Extending Context Window of Large Language Models via Positional Interpolationcited by 721
  12. 2021P-Tuning v2: Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Taskscited by 686
  13. 2023The Internal State of an LLM Knows When It's Lyingcited by 644
  14. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 574
  15. 2025Why Do Multi-Agent LLM Systems Fail?cited by 559
  16. 2024Executable Code Actions Elicit Better LLM Agentscited by 537
  17. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  18. 2023OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocationcited by 468
  19. 2023A Survey of Hallucination in Large Foundation Modelscited by 365
  20. 2024Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agentscited by 341
  21. 2023Analyzing and Mitigating Object Hallucination in Large Vision-Language Modelscited by 314
  22. 2023Benchmarking Large Language Models in Retrieval-Augmented Generationcited by 307
  23. 2024Chain of Agents: Large Language Models Collaborating on Long-Context Taskscited by 201
  24. 2025AgentSpec: Customizable Runtime Enforcement for Safe and Reliable LLM Agentscited by 196
  25. 2024Trial and Error: Exploration-Based Trajectory Optimization for LLM Agentscited by 194
  26. 2025Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systemscited by 170
  27. 2024Agent AI: Surveying the Horizons of Multimodal Interactioncited by 167
  28. 2023Conformal Language Modelingcited by 163
  29. 2023Take a Step Back: Evoking Reasoning via Abstraction in Large Language Modelscited by 157
  30. 2023EconAgent: Large Language Model-Empowered Agents for Simulating Macroeconomic Activitiescited by 154
  31. 2023Recommender AI Agent: Integrating Large Language Models for Interactive Recommendationscited by 130
  32. 2024Cut the Crap: An Economical Communication Pipeline for LLM-based Multi-Agent Systemscited by 129
  33. 2024AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathwayscited by 122
  34. 2023Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sourcescited by 121
  35. 2025Where LLM Agents Fail and How They can Learn From Failurescited by 118
  36. 2024G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networkscited by 110
  37. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?cited by 105
  38. 2024ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretabilitycited by 100

50 most cited of 85 All 85 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025A Survey on AgentOps: Categorization, Challenges, and Future Directions
  2. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challenges
  3. 2025Large Language Model Agent: A Survey on Methodology, Applications and Challenges
  4. 2026AgentFactory: Towards Automated Agentic System Design and Optimization
  5. 2025LLM-based Agentic Reasoning Frameworks: A Survey from Methods to Scenarios
  6. 2024Practical Considerations for Agentic LLM Systems
  7. 2024Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects
  8. 2026Who Broke the System? Failure Localization in LLM-Based Multi-Agent Systems