发表机构
Fujian Key Laboratory of Urban Intelligent Sensing and Computing, Xiamen University; Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University; School of Computer, National University of Defense Technology（厦门大学; 厦门大学; 国防科技大学计算机学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FlowMAS提出基于生成流网络的多智能体工作流拓扑学习方法，通过好奇心驱动探索和信息引导优化，在六个基准数据集上优于多个基线。
AI 中文摘要
自动化多智能体系统在可扩展性和适应性方面相比手动设计的系统具有明显优势，但现有的工作流拓扑方法仍面临重要限制。基于搜索的方法通常计算成本高昂，基于文本梯度的方法依赖粗粒度的反馈，而现有的基于生成的方法并不适合具有复杂依赖关系的离散工作流拓扑。为解决这些限制，我们提出了FlowMAS，一种基于生成流网络（GFlowNets）的多智能体工作流拓扑方法。FlowMAS将工作流生成建模为拓扑空间上的奖励引导流，并引入了三个组件：基于GFlowNet的拓扑生成主干、用于结构感知探索的好奇心驱动模块，以及用于评估中间拓扑的信息引导优化模块。具体而言，好奇心驱动模块鼓励探索结构新颖的工作流，而信息引导模块则衡量不同操作符的信息贡献和通信效率，以支持更具信息性和有效性的协作模式。在三个LLM骨干的六个基准数据集上的实验表明，FlowMAS持续优于多个基线。
英文摘要
Automated multi-agent systems offer clear advantages over manually designed ones in scalability and adaptability, but existing workflow topology methods still face important limitations. Search-based methods are often computationally expensive, textual-gradient-based methods rely on coarse-grained feedback, and existing generation-based methods are not well suited to discrete workflow topologies with complex dependencies. To address these limitations, we propose FlowMAS, a multi-agent workflow topology method based on Generative Flow Networks (GFlowNets). FlowMAS models workflow generation as reward-guided flow over the topology space and introduces three components: a GFlowNet-based topology generation backbone, a curiosity-driven module for structure-aware exploration, and an information-guided optimization module for evaluating intermediate topologies. Concretely, the curiosity-driven module encourages exploration of structurally novel workflows, while the information-guided module measures both the information contribution and the communication efficiency of different operators to favor more informative and effective collaboration patterns. Experiments on six benchmark datasets with three LLM backbones show that FlowMAS consistently outperforms multiple baselines.
