发表机构
Wuhan University; Central China Normal University; University of Oulu（武汉大学; 华中师范大学; 奥卢大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究通过实证分析21个开源基于LLM的多智能体系统中的944个问题，发现编排与执行问题最常见，工作流、工具集成和记忆问题是主要成因，优化工作流是主要解决方案，并提出改进建议。
AI 中文摘要
随着基于大语言模型的多智能体系统（MAS）的发展，越来越多的开源项目采用多智能体架构作为其核心功能的基础。尽管关于MAS的研究和实践已引起广泛关注，但有限的研究探讨了开源基于LLM的MAS实践者所面临的挑战、这些挑战的原因以及潜在解决方案。为弥补这一空白，我们进行了一项实证研究，以理解实践者在开发和利用开源基于LLM的MAS时遇到的问题、这些问题的可能原因以及潜在解决方案。我们收集了来自21个开源基于LLM的MAS的22,848个已关闭问题，并采用自动和手动相结合的过滤方法，将数据集缩减至944个与基于LLM的MAS相关的问题。随后，我们分析了这些问题，以理解实践者频繁遇到的问题、其根本原因及潜在解决方案。我们的研究结果显示：（1）编排与执行问题是最常见的实践者面临的问题；（2）工作流问题、工具集成问题和记忆问题被识别为最频繁的问题原因；（3）优化工作流是解决问题的主要方案。基于研究结果，我们为实践者和研究人员提出了基于实证的启示，旨在改进基于LLM的MAS中的编排、工具集成和记忆机制。
英文摘要
With the advancement of LLM-based multi-agent systems (MAS), an increasing number of opensource projects are adopting multi-agent architectures as the foundation of their core functionality. Although research and practice on MAS have attracted considerable attention, limited studies have explored the challenges faced by practitioners of open-source LLM-based MAS, the causes of these challenges, and potential solutions. To address this gap,we conducted an empirical study to understand the issues that practitioners encounter when developing and using open-source LLM-based MAS, the possible causes of these issues, and potential solutions. We collected 22,848 closed issues from 21 open-source LLM-basedMASand applied a mixed automated and manual filtering approach to reduce the dataset to 944 issues related to LLM-based MAS.We then analyzed these issues to understand the frequent issues encountered by practitioners, their underlying causes, and potential solutions. Our study results show that (1) Orchestration & Execution Issue is the most common issue faced by practitioners, (2) Workflow Problem, Tool Integration Problem, and Memory Problem are identified as the most frequent causes of the issues, and (3) Optimize Workflow is the predominant solution to the issues. Based on the study results, we derive empirically grounded implications for practitioners and researchers aimed at improving orchestration, tool integration, and memory mechanisms in LLM-based MAS.
Comments30 pages, 4 images, 10 tables, Manuscript submitted to a journal (2026)
