Abstract: Large Language Model-based Multi-Agent Systems have demonstrated significant potential in handling complex tasks. Their distributed nature and interaction uncertainty can lead to diverse anomalies, threatening system reliability. To systematically identify and classify such anomalies, this study conducts a comprehensive review. The research selected seven representative multi-agent systems and their corresponding datasets, collecting 13,418 operational traces, and employed a hybrid data analysis method combining preliminary LLM analysis with expert manual validation. A fine-grained, four-level anomaly classification framework was constructed, encompassing Model Understanding and Perception Anomalies, Agent Interaction Anomalies, Task Execution Anomalies, and External Environment Anomalies, and typical cases were analyzed to reveal the underlying logic and external causes of each type of anomaly. Statistical analysis indicates that Model Understanding and Perception Anomalies account for the highest proportion, with "Context Hallucination" and "Task Instruction Misunderstanding" being the primary issues. Agent Interaction Anomalies represent 16.8%, primarily caused by "Information Concealment." Task Execution Anomalies make up 27.1%, mainly characterized by "Repetitive Decision Errors." External Environment Anomalies constitute 18.3%, with "Memory Conflicts" as the predominant factor. In addition, model perception and understanding anomalies often act as root causes, triggering anomalies at other levels, highlighting the importance of enhancing the fundamental capabilities of the model. These classification and root cause analysis aims at providing theoretical support and practical reference for building highly reliable LLM-based multi-agent systems.

摘要： 基于大语言模型的多智能体系统虽在处理复杂任务方面展现巨大潜力，但其分布式特性与交互不确定性易引发多样化异常，威胁系统可靠性。为系统化识别并分类此种异常，本研究进行全面综述。研究选取七个代表性多智能体系统及相应数据集，收集13,418段运行轨迹，采用LLM初步分析与专家人工校验相结合的方法进行数据分析。研究构建了一个涵盖模型理解感知异常、智能体交互异常、任务执行异常和外部环境异常四个层级的细粒度异常分类框架，并结合典型案例揭示了各类异常产生的内在逻辑与外部诱因。统计分析显示，模型理解感知异常占比最高，其中“上下文幻觉”和“任务指令误解”是主要问题；智能体交互异常占16.8%，“信息隐瞒”是主因；任务执行异常占27.1%，主要表现为“决策重复出错”；外部环境异常占18.3%，以“记忆冲突”为主。此外，模型理解感知异常常作为根源性诱因，引发其他层级的异常，凸显了提升模型基础能力的重要性。此分类和根源分析旨在为构建高可靠的基于大语言模型的多智能体系统提供理论支撑与实践参考。