1
\textsc{MasFACT}: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer
提出基于几何感知后验转移的持续多智能体拓扑学习方法，突破灾难性遗忘难题。
arXiv:2605.17361v1 Announce Type: new Abstract: Multi-agent systems (MAS) powered by large language models (LLMs) have emerged as a powerful paradigm …