← 피드로
[Submitted on 16 Feb 2026 (v1), last revised 22 Aug 2026 (this version, v4)]
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.
Submission history
From: Xingjian Wu [view email]
[v1]
Mon, 16 Feb 2026 12:13:03 UTC (2,287 KB)
[v2]
Sat, 21 Feb 2026 10:26:47 UTC (2,287 KB)
[v3]
Tue, 24 Feb 2026 03:02:02 UTC (2,287 KB)
[v4]
Sat, 22 Aug 2026 14:05:47 UTC (2,284 KB)
추출 본문 · 출처: arxiv.org · https://arxiv.org/abs/2602.14681