Skip to content
Hot eventLive

提出多智能体系统动态专家剪枝方法 DEP

1 reports1 sources16 hr ago updated

Get the story

AI overview

2026年10月5日,研究者在 arXiv(Multiagent Systems)发表论文,提出面向多智能体系统的动态专家剪枝方法 Dynamic Expert Pruning(DEP)。该方法针对混合专家(MoE)架构在多智能体系统中静态剪枝失效的问题,利用智能体的 system 与 task prompt 来预测所需专家,从而实现动态剪枝。目前报道仅涉及该方法的提出与基本思路,未披露实验数据或后续验证进展。

Generated from reports · updated 16 hr ago

Timeline

Follow the coverage from different angles.

Oct 5, 2026
  1. arXiv · Multiagent Systems
    面向多智能体系统的动态专家剪枝方法 DEP

    研究者提出 Dynamic Expert Pruning(DEP),针对 MoE 架构在多智能体系统中静态剪枝失效的问题,利用智能体的 system 与 task prompt 预测所需专家。

Heat trend

Current heat 7·Comparable peak 10(Oct 5)·Comparable change over 24 hours –

02.557.510Oct5Oct5Oct5Oct6

The trend compares only the same participants observed continuously; its range may be smaller than the current heat count. Move or click on the chart to inspect hourly heat; use the left and right arrow keys to switch.