首次系统分析多智能体大模型失败原因，揭示14类核心问题。
Why Do Multi-Agent LLM Systems Fail?
- 构建首个多智能体失败分类体系MAST，划分三类14种故障模式。
- 基于1600+轨迹数据，发现不同模型在任务中普遍存在协同失效。
- 开源数据集与标注工具，助力下一代智能体系统研发。
尽管多智能体大模型系统（MAS）备受关注，其在主流基准上的性能提升却有限。为理解其失败根源，我们构建了MAST-Data——一个涵盖7个主流框架的超1600条标注轨迹的综合性数据集，首次系统刻画了多智能体系统的失败动态。为实现失败模式的系统分类，我们提出首个多智能体系统失败分类法（MAST），基于150条轨迹的深度分析，结合专家人工标注，达成高一致性（kappa = 0.88），识别出14种独特故障模式，归为三类：系统设计缺陷、智能体间目标错位、任务验证缺失。为支持可扩展标注，我们开发了大模型作为裁判的流水线，与人工标注高度一致。利用MAST与MAST-Data，我们分析了GPT4、Claude 3、Qwen2.5、CodeLlama等模型在编程、数学和通用任务中的失败模式，揭示优化空间。研究指出，现有失败需更复杂解决方案，为未来研究提供清晰路线图。我们已公开发布完整数据集、分类体系及大模型标注工具，推动该领域广泛研究与发展。
原文摘要 · Abstract (English)
Despite enthusiasm for Multi-Agent LLM Systems (MAS), their performance gains on popular benchmarks are often minimal. This gap highlights a critical need for a principled understanding of why MAS fail. Addressing this question requires systematic identification and analysis of failure patterns. We introduce MAST-Data, a comprehensive dataset of 1600+ annotated traces collected across 7 popular MAS frameworks. MAST-Data is the first multi-agent system dataset to outline the failure dynamics in MAS for guiding the development of better future systems. To enable systematic classification of failures for MAST-Data, we build the first Multi-Agent System Failure Taxonomy (MAST). We develop MAST through rigorous analysis of 150 traces, guided closely by expert human annotators and validated by high inter-annotator agreement (kappa = 0.88). This process identifies 14 unique modes, clustered into 3 categories: (i) system design issues, (ii) inter-agent misalignment, and (iii) task verification. To enable scalable annotation, we develop an LLM-as-a-Judge pipeline with high agreement with human annotations. We leverage MAST and MAST-Data to analyze failure patterns across models (GPT4, Claude 3, Qwen2.5, CodeLlama) and tasks (coding, math, general agent), demonstrating improvement headrooms from better MAS design. Our analysis provides insights revealing that identified failures require more sophisticated solutions, highlighting a clear roadmap for future research. We publicly release our comprehensive dataset (MAST-Data), the MAST, and our LLM annotator to facilitate widespread research and development in MAS.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。