LLM-powered Multi-Agent Systems (MAS) have emerged as an effective approach towards collaborative intelligence, and have attracted wide research interests. Among them, ``self-evolving'' MAS, treated as a more flexible and powerful technical route, can construct task-adaptive workflows or communication topologies, instead of relying on a predefined static structue template. Current self-evolving MAS mainly focus on Spatial Evolving or Temporal Evolving paradigm, which only considers the single dimension of evolution and does not fully incentivize LLMs' collaborative capability. In this work, we start from a novel Spatio-Temporal perspective by proposing ST-EVO, which supports dialogue-wise communication scheduling with a compact yet powerful flow-matching based Scheduler. To make precise Spatio-Temporal scheduling, ST-EVO can also perceive the uncertainty of MAS, and possesses self-feedback ability to learn from accumulated experience. Extensive experiments on nine benchmarks demonstrate the state-of-the-art performance of ST-EVO, achieving about 5%--25% accuracy improvement.

翻译：基于大语言模型的多智能体系统已成为实现协同智能的有效途径，并引起了广泛的研究兴趣。其中，“自演化”多智能体系统被视为一种更灵活、更强大的技术路线，它能够构建任务自适应的工作流程或通信拓扑，而非依赖预定义的静态结构模板。当前的自演化多智能体系统主要集中于空间演化或时间演化范式，仅考虑单一维度的演化，未能充分激发大语言模型的协同潜力。本工作从新颖的时空视角出发，提出ST-EVO框架，该框架通过一个紧凑而强大的基于流匹配的调度器，支持对话粒度的通信调度。为了实现精确的时空调度，ST-EVO还能感知多智能体系统的不确定性，并具备自反馈能力以从累积经验中学习。在九个基准测试上的大量实验证明了ST-EVO的先进性能，实现了约5%至25%的准确率提升。