AI RESEARCH
AgentSlimming: Towards Efficient and Cost-Aware Multi-Agent Systems
arXiv CS.LG
•
ArXi:2605.08813v1 Announce Type: new Large Language Model-based Multi-Agent Systems (MAS) have nstrated remarkable capabilities in complex tasks. However, manually designing optimal communication topologies is labor-intensive, while automated expansion methods often result in bloated structures with redundant agents, leading to excessive token consumption. To address this problem, we