Agentic AI systems combine LLM-based reasoning, orchestration, tool invocation, and interaction with external environments. These systems introduce faults that are difficult to characterize using existing taxonomies. To address this gap, we present an empirical study of faults in agentic AI systems. We collected 13,602 issues and pull requests from 40 repositories and, using stratified sampling, selected 385 faults for analysis. Through grounded theory, we derived taxonomies of fault types, symptoms, and root causes. We then used Apriori-based association rule mining to identify relationships among faults, symptoms, and root causes, and validated the taxonomy through a developer study with 145 practitioners. Our analysis produced a taxonomy of 34 fault types, organized into four architectural dimensions. These faults manifested as failures in structured-output interpretation, tool calls, runtime execution, and exception handling, with root causes including data schema mismatches, dependency drift, state management complexity, and model interface instability. Furthermore, association rules showed recurring cross-component propagation, linking structured data, dependency, and state management faults to their symptoms and root causes. Practitioners considered the taxonomy representative of agentic AI failures and suggested refinements related to multi-agent coordination and observability. These findings provide an empirical basis for diagnosing faults and improving reliability in agentic AI systems.

翻译：智能体AI系统结合了基于大语言模型的推理、编排、工具调用以及与外部环境的交互。这些系统引入了现有分类体系难以表征的故障类型。为填补这一空白，我们开展了针对智能体AI系统故障的实证研究。我们从40个代码仓库中收集了13,602个议题（issues）和拉取请求（pull requests），通过分层抽样选取385个故障案例进行分析。运用扎根理论，我们推导出故障类型、症状及根本原因的分类体系，并采用基于Apriori算法的关联规则挖掘技术识别故障、症状与根本原因之间的关联关系，同时通过覆盖145位从业者的开发者研究验证了该分类体系。分析结果显示，我们构建的分类体系包含34种故障类型，可归入四个架构维度。这些故障表现为结构化输出解析失败、工具调用异常、运行时执行错误及异常处理失效，其根本原因涵盖数据模式不匹配、依赖项漂移、状态管理复杂度及模型接口不稳定性。关联规则进一步揭示出跨组件传播的重复模式，将结构化数据、依赖管理和状态管理类故障与其症状及根本原因相关联。从业者认为该分类体系能够有效表征智能体AI系统的故障特征，并提出了关于多智能体协调与可观测性方面的改进建议。这些发现为诊断智能体AI系统故障、提升系统可靠性提供了实证基础。