mlsanityData to 7 Oct 2026

When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling

arXiv 2601.15232 ↗First posted 21 Jan 2026cs.SEcited by 6

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

Abstract (arXiv)

Large Language Models (LLMs) have revolutionized intelligent application development. While standalone LLMs cannot perform any actions, LLM agents address the limitation by integrating tools. However, debugging LLM agents is difficult and costly, as the field is still in its early stages and the community is underdeveloped. To understand the bugs encountered during agent development, we present the first comprehensive study of bug types, root causes, and effects in LLM agent-based software. We collected and analyzed 1,268 bug-related posts and code snippets from Stack Overflow, GitHub, and Hugging Face forums, focused on LLM agents built with seven widely used LLM frameworks as well as custom implementations. For a deeper analysis, we have also studied the component of the LLM agent where the bug occurred, along with the programming language and framework. This study also investigates the feasibility of automating bug identification. For that, we have built a ReAct agent named BugReAct, equipped with adequate external tools to determine whether it can detect and annotate the bugs in our dataset. According to our study, we found that BugReAct equipped with Gemini 2.5 Flash achieved a remarkable performance in annotating bug characteristics with an average cost of 0.01 USD per post/code snippet.

Key facts. Cited by 6 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 35 of its 98 references that are in the map. First posted on arXiv 21 Jan 2026.

Builds on

35 of 98 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Where LLM Agents Fail and How They can Learn From Failures29 Sep
  2. 2025Understanding Software Engineering Agents: A Study of Thought-Action-Result Trajectories23 Jun
  3. 2025Can Agents Fix Agent Issues?27 May
  4. 2025TRAIL: Trace Reasoning and Agentic Issue Localization13 May
  5. 2025Why Do Multi-Agent LLM Systems Fail?17 Mar
  6. 2025Interactive Debugging and Steering of Multi-Agent AI Systems3 Mar
  7. 2024Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents24 Dec
  8. 2024Large Language Model-Based Agents for Software Engineering: A Survey4 Sep
  9. 2024SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering6 May

Other references · 26

  1. 2022Training language models to follow instructions with human feedbackcited by 15,712
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  4. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  5. 2023SWE-bench: Can Language Models Resolve Real-World GitHub Issues?cited by 3,193
  6. 2024A Survey on LLM-as-a-Judgecited by 1,384
  7. 2020CodeBERT: A Pre-Trained Model for Programming and Natural Languagescited by 1,286
  8. 2021CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generationcited by 890
  9. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 814
  10. 2024LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methodscited by 451
  11. 2023JudgeLM: Fine-tuned Large Language Models are Scalable Judgescited by 351
  12. 2024AutoCodeRover: Autonomous Program Improvementcited by 272
14 more
  1. 2018Auto-Keras: An Efficient Neural Architecture Search Systemcited by 169
  2. 2023An Empirical Study of the Non-determinism of ChatGPT in Code Generationcited by 134
  3. 2019Taxonomy of Real Faults in Deep Learning Systemscited by 90
  4. 2019A Comprehensive Study on Deep Learning Bug Characteristicscited by 65
  5. 2024Granite-Function Calling Model: Introducing Function Calling Abilities via Multi-task Learning of Granular Taskscited by 52
  6. 2025The relationship between reasoning and performance in large language models--o3 (mini) thinks harder, not longercited by 39
  7. 2025RAFFLES: Reasoning-based Attribution of Faults for LLM Systemscited by 19
  8. 2025Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolutioncited by 11
  9. 2024Learning to Correct for QA Reasoning with Black-box LLMscited by 6
  10. 2024Towards Understanding the Impact of Data Bugs on Deep Learning Models in Software Engineeringcited by 6
  11. 2024muPRL: A Mutation Testing Pipeline for Deep Reinforcement Learning based on Real Faultscited by 5
  12. 2025The Foundation Cracks: A Comprehensive Study on Bugs and Testing Practices in LLM Librariescited by 3
  13. 2024The Impact Of Bug Localization Based on Crash Report Mining: A Developers' Perspectivecited by 2
  14. 2020Verifying Correct Usage of Context-Free API Protocols (Extended Version)cited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 6.

6 papers.

  1. 2026From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flawscited by 21
  2. 2026Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomycited by 5
  3. 2026Understanding Bugs in Modern Agentic Frameworks: A Study of Symptoms, Root Causes, and Triggering Conditionscited by 1
  4. 2026SelfHeal: Empirical Fix Pattern Analysis and Bug Repair in LLM Agentscited by 1
  5. 2026Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reportscited by 1
  6. 2026Hierarchical Fault Detection and Diagnosis for Transformer Architecturescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024An Empirical Study on LLM-based Agents for Automated Bug Fixing
  2. 2026Tangent: An Empirical Study of Testing Practices for LLM-Based Agent Applications
  3. 2026Where Agent Frameworks Fall Short: Examining Functional Challenges and Usability Concerns
  4. 2026Evaluating LLM Agents on Automated Software Analysis Tasks
  5. 2024Agents in Software Engineering: Survey, Landscape, and Vision
  6. 2024From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future
  7. 2025LLM Agents for Automated Web Vulnerability Reproduction: Are We There Yet?
  8. 2025ToolFuzz -- Automated Agent Tool Testing