# Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents

arXiv: https://arxiv.org/abs/2412.18371 · HTML: https://mlsanity.com/paper/2412.18371/

## Key facts

- Cited by 16 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 31 of its 61 references that are in the map.
- First posted on arXiv 24 Dec 2024.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 30 of 31)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Code Llama: Open Foundation Models for Code](https://mlsanity.com/paper/2308.12950/) (2023)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [StarCoder: may the source be with you!](https://mlsanity.com/paper/2305.06161/) (2023)
- [Large Language Model based Multi-Agents: A Survey of Progress and Challenges](https://mlsanity.com/paper/2402.01680/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Bases](https://mlsanity.com/paper/2407.12784/) (2024)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Agentless: Demystifying LLM-based Software Engineering Agents](https://mlsanity.com/paper/2407.01489/) (2024)
- [Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents](https://mlsanity.com/paper/2410.02644/) (2024)
- [Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security](https://mlsanity.com/paper/2401.05459/) (2024)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead](https://mlsanity.com/paper/2404.04834/) (2024)
- [AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents](https://mlsanity.com/paper/2406.13352/) (2024)
- [Exploring Large Language Model based Intelligent Agents: Definitions, Methods, and Prospects](https://mlsanity.com/paper/2401.03428/) (2024)
- [AI Agents Under Threat: A Survey of Key Security Challenges and Future Pathways](https://mlsanity.com/paper/2406.02630/) (2024)
- [AIOS: LLM Agent Operating System](https://mlsanity.com/paper/2403.16971/) (2024)
- [From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future](https://mlsanity.com/paper/2408.02479/) (2024)
- [Cognitive Mirage: A Review of Hallucinations in Large Language Models](https://mlsanity.com/paper/2309.06794/) (2023)
- [KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents](https://mlsanity.com/paper/2403.03101/) (2024)
- [Risks of AI Scientists: Prioritizing Safeguarding Over Autonomy](https://mlsanity.com/paper/2402.04247/) (2024)
- [Moral Alignment for LLM Agents](https://mlsanity.com/paper/2410.01639/) (2024)
- [Large Model Based Agents: State-of-the-Art, Cooperation Paradigms, Security and Privacy, and Future Trends](https://mlsanity.com/paper/2409.14457/) (2024)
- [An Empirical Study on Challenges for LLM Application Developers](https://mlsanity.com/paper/2408.05002/) (2024)
- [CEBench: A Benchmarking Toolkit for the Cost-Effectiveness of LLM Pipelines](https://mlsanity.com/paper/2407.12797/) (2024)
- [A Multi-Agent Approach to Fault Localization via Graph-Based Retrieval and Reflexion](https://mlsanity.com/paper/2409.13642/) (2024)
- [Hyperion: Unveiling DApp Inconsistencies using LLM and Dataflow-Guided Symbolic Execution](https://mlsanity.com/paper/2408.06037/) (2024)
- [Demystifying and Detecting Cryptographic Defects in Ethereum Smart Contracts](https://mlsanity.com/paper/2408.04939/) (2024)

## Built on by (most cited first, 16 of 16)

- [Where LLM Agents Fail and How They can Learn From Failures](https://mlsanity.com/paper/2509.25370/) (2025)
- [AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems](https://mlsanity.com/paper/2605.08715/) (2026)
- [When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling](https://mlsanity.com/paper/2601.15232/) (2026)
- [Automated structural testing of LLM-based agents: methods, framework, and case studies](https://mlsanity.com/paper/2601.18827/) (2026)
- [LIDL: LLM Integration Defect Localization via Knowledge Graph-Enhanced Multi-Agent Analysis](https://mlsanity.com/paper/2601.05539/) (2026)
- [A Self-Healing Framework for Reliable LLM-Based Autonomous Agents](https://mlsanity.com/paper/2605.06737/) (2026)
- [AgentFlow: Building Agent Dependency Graphs for Static Analysis of Agent Programs](https://mlsanity.com/paper/2607.01640/) (2026)
- [Do Agent Benchmarks Do What They Say? An Executable-Contract Audit of Tool-Using Agent Environments](https://mlsanity.com/paper/2609.37315/) (2026)
- [Fine-Tuning LLMs to Analyze Multiple Dimensions of Code Review: A Maximum Entropy Regulated Long Chain-of-Thought Approach](https://mlsanity.com/paper/2509.21170/) (2025)
- [A Taxonomy of Runtime Faults in Model Context Protocol Servers](https://mlsanity.com/paper/2606.05339/) (2026)
- [HPFA: Hypergraph-Based Paired Failure Attribution for LLM Reasoning](https://mlsanity.com/paper/2608.02026/) (2026)
- [Specification and Detection of LLM Code Smells](https://mlsanity.com/paper/2512.18020/) (2025)
- [PYTHALAB-MERA: Validation-Grounded Memory, Retrieval, and Acceptance Control for Frozen-LLM Coding Agents](https://mlsanity.com/paper/2605.08468/) (2026)
- [LLM Code Smells: A Taxonomy and Detection Approach](https://mlsanity.com/paper/2605.22976/) (2026)
- [SkillSpec: Intent-Masked Specification Reasoning for Agent Skill Correctness](https://mlsanity.com/paper/2609.06052/) (2026)
- [Do Tool Calls Execute as Intended? Measuring and Repairing Intent-Execution Correspondence in LLM Agents](https://mlsanity.com/paper/2610.04375/) (2026)

## Abstract (arXiv)

AI agents are systems capable of perceiving their environment, autonomously planning and executing tasks. Recent advancements in LLM have introduced a transformative paradigm for AI agents, enabling them to interact with external resources and tools through prompts. In such agents, the workflow integrates developer-written code, which manages framework construction and logic control, with LLM-generated natural language that enhances dynamic decision-making and interaction. However, discrepancies between developer-implemented logic and the dynamically generated content of LLMs in terms of behavior and expected outcomes can lead to defects, such as tool invocation failures and task execution errors. These issues introduce specific risks, leading to various defects in LLM-based AI Agents, such as service interruptions. Despite the importance of these issues, there is a lack of systematic work that focuses on analyzing LLM-based AI Agents to uncover defects in their code. In this paper, we present the first study focused on identifying and detecting defects in LLM Agents. We collected and analyzed 6,854 relevant posts from StackOverflow to define 8 types of agent defects. For each type, we provided detailed descriptions with an example. Then, we designed a static analysis tool, named Agentable, to detect the defects. Agentable leverages Code Property Graphs and LLMs to analyze Agent workflows by efficiently identifying specific code patterns and analyzing natural language descriptions. To evaluate Agentable, we constructed two datasets: AgentSet, consists of 84 real-world Agents, and AgentTest, which contains 78 Agents specifically designed to include various types of defects. Our results show that Agentable achieved an overall accuracy of 88.79% and a recall rate of 91.03%. Furthermore, our analysis reveals the 889 defects of the AgentSet, highlighting the prevalence of these defects.