一句话：对五个主流智能体框架的 409 个缺陷进行实证研究，提出五层架构抽象与缺陷分类法，并分析触发条件。
现代智能体框架（如 CrewAI、AutoGen）已演化为复杂的自主多智能体系统，带来超出早期 LLM 流水线库的可靠性挑战，而现有实证研究多聚焦早期库或任务级缺陷。本文研究五个代表性框架中 409 个已修复缺陷，提出五层架构抽象与缺陷分类法，识别出此前未报告的症状类别（意外执行顺序、用户配置被忽略、不完整/错误轨迹）与智能体特有根因（模型相关故障、认知上下文管理不当、编排故障）。模型集成层最易出错，但修复时测试覆盖仅 47%，存在验证缺口；各框架的症状、根因与易错组件高度一致（JS 相似度 0.62–0.88）。文章还首次系统研究触发条件，给出跨元素配置、输入模式与操作的易错因子组合并验证其可迁移性。
Modern agentic frameworks such as CrewAI and AutoGen have evolved into complex, autonomous multi-agent systems, introducing reliability challenges that go beyond earlier pipeline-based LLM libraries. However, existing empirical studies focus on earlier LLM libraries or task-level bugs, leaving the unique complexities of these agentic frameworks unexplored. We present a comprehensive study of 409 fixed bugs across five representative agentic frameworks, proposing a five-layer architectural abstraction. Our taxonomy identifies previously unreported symptom categories—Unexpected Execution Sequence, User Configuration Ignored, and Incomplete/Incorrect Trace—and isolates agent-specific root causes including Model-Related Fault, Cognitive Context Mismanagement, and Orchestration Fault. Notably, the model integration layer is the most bug-prone yet receives disproportionately low test inclusion rate during bug fixing (47%), revealing a critical validation gap. Despite varying design paradigms, bug symptoms, root causes, and bug-prone components show substantial cross-framework consistency (JS similarity 0.62–0.88). Finally, we present the first systematic study of bug-triggering conditions, identifying error-prone factor combinations across element configurations, input patterns, and operations, and demonstrate their transferability across frameworks, providing a foundation for test oracle design and cross-framework benchmark.
@inproceedings{paperbot12508,
title = {Understanding Bugs in Modern Agentic Frameworks: A Study of Symptoms, Root Causes, and Triggering Conditions},
author = {Xiaowen Zhang and Hannuo Zhang and Shin Hwei Tan},
booktitle = {ASE},
year = {2026},
doi = {10.1145/3832783.3834378}
}