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

2026-02-16

AI Summary

Existing self-evolving multi-agent systems typically evolve along only one dimension—either spatial or temporal—limiting their ability to fully harness the collaborative potential of large language models. To address this, this work proposes ST-EVO, a novel framework that introduces, for the first time, a spatiotemporal co-evolution mechanism to dynamically construct communication topologies. ST-EVO employs a flow-matching scheduler for dialogue-level communication orchestration and integrates uncertainty-awareness with a self-feedback learning module to refine collaborative structures. Evaluated across nine benchmark datasets, the method achieves significant performance gains, improving accuracy by 5%–25% over existing approaches, thereby demonstrating its effectiveness in enhancing both the efficiency and adaptability of multi-agent collaboration.

Technology Category

• Multiagent Systems: Agent Communication
• Machine Learning: Evolutionary Learning
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Models for Web evolution

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.

Problem

• Multi-Agent Systems
• Spatio-Temporal Evolution
• Communication Topologies
• Self-Evolving
• LLM-powered

Innovation

• Spatio-Temporal Evolution
• Flow-Matching Scheduler
• Self-Evolving Multi-Agent Systems
• Uncertainty-Aware Communication
• LLM-Powered MAS