ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917290171170816 |
|---|---|
| author | Wu, Xingjian Liu, Xvyuan Lu, Junkai Wang, Siyuan Qiu, Xiangfei Shu, Yang Hu, Jilin Guo, Chenjuan Yang, Bin |
| author_facet | Wu, Xingjian Liu, Xvyuan Lu, Junkai Wang, Siyuan Qiu, Xiangfei Shu, Yang Hu, Jilin Guo, Chenjuan Yang, Bin |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_14681 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies Wu, Xingjian Liu, Xvyuan Lu, Junkai Wang, Siyuan Qiu, Xiangfei Shu, Yang Hu, Jilin Guo, Chenjuan Yang, Bin Multiagent Systems Artificial Intelligence 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. |
| title | ST-EVO: Towards Generative Spatio-Temporal Evolution of Multi-Agent Communication Topologies |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2602.14681 |