arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.12307cs.MAcs.CLcs.LG
收藏

重新思考多智能体工作流的价值:一个强大的单智能体基线

Rethinking the Value of Multi-Agent Workflow: A Strong Single Agent Baseline

The University of Texas at Austin(德克萨斯大学奥斯汀分校);Amazon(亚马逊);Emory University(埃默里大学);Northeastern University(东北大学);Georgia Institute of Technology(佐治亚理工学院)

Jiawei Xu, Arief Koesdwiady, Sisong Bei, Yan Han, Baixiang Huang, Dakuo Wang, Yutong Chen, Zheshen Wang, Peihao Wang, Pan Li, Ying Ding

AI总结:

本研究通过单个代理的多轮对话模拟多智能体工作流,提出OneFlow算法,实现高效且准确的多代理流程,为多智能体系统研究提供强基线。

摘要:

最近基于大语言模型的多智能体系统(MAS)的进展表明,由多个具有不同角色、工具和通信模式的大语言模型代理组成的流程可以在复杂任务上超越单一大语言模型基线。然而,大多数框架都是同质的,其中所有代理共享相同的基大语言模型,仅在提示、工具和流程中的位置上有所不同。这引发了这样的问题:这样的流程是否可以通过单个代理的多轮对话来模拟。我们在这七个基准上进行了调查,涵盖编程、数学、一般问题回答、领域特定推理和现实世界规划和工具使用。我们的结果表明,单个代理可以通过KV缓存重用获得效率优势,可以达到同质流程的性能,甚至可以匹配自动优化的异质流程的性能。基于这一发现,我们提出了OneFlow算法,该算法自动为单个代理执行定制流程,与现有自动多代理设计框架相比,降低了推理成本,而不会牺牲准确性。这些结果将单大语言模型实现的多代理流程定位为MAS研究的强大基线。我们还注意到,单大语言模型方法由于不同大语言模型之间缺乏KV缓存共享,无法捕捉异质流程,这突显了未来在开发真正异质多代理系统方面的机遇。

英文摘要:

Recent advances in LLM-based multi-agent systems (MAS) show that workflows composed of multiple LLM agents with distinct roles, tools, and communication patterns can outperform single-LLM baselines on complex tasks. However, most frameworks are homogeneous, where all agents share the same base LLM and differ only in prompts, tools, and positions in the workflow. This raises the question of whether such workflows can be simulated by a single agent through multi-turn conversations. We investigate this across seven benchmarks spanning coding, mathematics, general question answering, domain-specific reasoning, and real-world planning and tool use. Our results show that a single agent can reach the performance of homogeneous workflows with an efficiency advantage from KV cache reuse, and can even match the performance of an automatically optimized heterogeneous workflow. Building on this finding, we propose \textbf{OneFlow}, an algorithm that automatically tailors workflows for single-agent execution, reducing inference costs compared to existing automatic multi-agent design frameworks without trading off accuracy. These results position the single-LLM implementation of multi-agent workflows as a strong baseline for MAS research. We also note that single-LLM methods cannot capture heterogeneous workflows due to the lack of KV cache sharing across different LLMs, highlighting future opportunities in developing \textit{truly} heterogeneous multi-agent systems.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑