ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies

TL;DR

ST-EVO introduces a novel spatio-temporal framework for self-evolving multi-agent systems, enabling task-adaptive communication topologies and achieving significant accuracy improvements across benchmarks.

Contribution

It proposes a new spatio-temporal evolution approach with a flow-matching scheduler and self-feedback, advancing beyond existing spatial or temporal-only paradigms.

Findings

Achieves 5-25% accuracy improvements on nine benchmarks.

Supports dialogue-wise communication scheduling.

Perceives uncertainty and learns from experience.

Abstract

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.