mlsanityData to 14 Oct 2026

Demystifying the Lifecycle of Failures in Platform-Orchestrated Agentic Workflows

arXiv 2509.23735 ↗First posted 28 Sep 2025cs.AI cs.SEcited by 10

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

Abstract (arXiv)

Agentic workflows built on low-code orchestration platforms enable rapid development of multi-agent systems, but they also introduce new and poorly understood failure modes that hinder reliability and maintainability. Unlike traditional software systems, failures in agentic workflows often propagate across heterogeneous nodes through natural-language interactions, tool invocations, and dynamic control logic, making failure attribution and repair particularly challenging. In this paper, we present an empirical study of platform-orchestrated agentic workflows from a failure lifecycle perspective, with the goal of characterizing failure manifestations, identifying underlying root causes, and examining corresponding repair strategies. We present AgentFail, a dataset of 307 real-world failure cases collected from two representative agentic workflow platforms. Based on this dataset, we analyze failure patterns, root causes, and repair difficulty for various failure root causes and nodes in the workflow. Our findings reveal key failure mechanisms in agentic workflows and provide actionable guidelines for reliable failure repair, and real-world agentic workflow design.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 17 of its 33 references that are in the map. First posted on arXiv 28 Sep 2025.

Builds on

17 of 33 references.

Closest ancestors · 5

Same direction, newest first

  1. 2025AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?3 Sep
  2. 2025Why Do Multi-Agent LLM Systems Fail?17 Mar
  3. 2025Interactive Debugging and Steering of Multi-Agent AI Systems3 Mar
  4. 2024Agentless: Demystifying LLM-based Software Engineering Agents1 Jul
  5. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation16 Aug

Other references · 12

  1. 2021Evaluating Large Language Models Trained on Codecited by 8,320
  2. 2024A Survey on LLM-as-a-Judgecited by 1,423
  3. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
  4. 2023GAIA: a benchmark for General AI Assistantscited by 1,128
  5. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 392
  6. 2023AutoAgents: A Framework for Automatic Agent Generationcited by 216
  7. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 93
  8. 2024A Scalable Communication Protocol for Networks of Large Language Modelscited by 45
  9. 2024Adaptive In-conversation Team Building for Language Model Agentscited by 39
  10. 2025Exploring Autonomous Agents: A Closer Look at Why They Fail When Completing Taskscited by 20
  11. 2025Aegis: Taxonomy and Optimizations for Overcoming Agent-Environment Failures in LLM Agentscited by 10
  12. 2025Improving Model Alignment Through Collective Intelligence of Open-Source LLMScited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 10.

10 papers.

  1. 2026Are Tools All We Need? Unveiling the Tool-Use Tax in LLM Agentscited by 11
  2. 2026Efficient Failure Management for Multi-Agent Systems with Reasoning Trace Representationcited by 6
  3. 2026Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systemscited by 6
  4. 2026CUADebug: Diagnosing and Repairing Computer-Use Agent Failurescited by 4
  5. 2026Think Locally, Explain Globally: Graph-Guided LLM Investigations via Local Reasoning and Belief Propagationcited by 3
  6. 2026The Shadow Self: Intrinsic Value Misalignment in Large Language Model Agentscited by 1
  7. 2026Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agentscited by 1
  8. 2026SkillTV-Bench: Benchmarking How Well Judges Perform on Skill-Augmented Agentic Executioncited by 1
  9. 2026Diagnosis-Driven Automatic Repair for Agentic Workflow via Symbolic Inferencecited by 0
  10. 2026Beyond LLM-Based Reasoning: Lightweight GNNs for Agent Failure Attributioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Why Agentic Workflows Fail: A Taxonomy Derived from Literature and Empirical Data
  2. 2026AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking
  3. 2025An Empirical Study on Failures in Automated Issue Solving
  4. 2026A Self-Healing Framework for Reliable LLM-Based Autonomous Agents
  5. 2026GraphFlow: An Architecture for Formally Verifiable Visual Workflows Enabling Reliable Agentic AI Automation
  6. 2026Failure as a Process: An Anatomy of CLI Coding Agent Trajectories
  7. 2025AgentCompass: Towards Reliable Evaluation of Agentic Workflows in Production
  8. 2026Mnemosyne: Agentic Transaction Processing for Validating and Repairing AI-generated Workflows