Abstract:Large Language Model-based Multi-Agent Systems (MAS) have demonstrated 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 introduce \textbf{AgentSlimming}, a plug-and-play compression framework for graph-structured multi-agent workflows. Motivated by pruning and quantization in neural networks, AgentSlimming compresses workflows by first estimating the importance score of each agent with a hybrid mechanism, and then removes redundant agents or replaces them with low-cost ones, where each operation is validated using a baseline-anchored acceptance rule to prevent performance collapse. Experiments show that AgentSlimming reduces average token cost by up to 78.9\% with negligible performance degradation, and sometimes even improves accuracy, achieving a strong Pareto-optimal trade-off between cost and quality. \textit{Our code is publicly available at this https URL
| Subjects: | Machine Learning (cs.LG) |
| Cite as: | arXiv:2605.08813 [cs.LG] |
| (or arXiv:2605.08813v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.08813 arXiv-issued DOI via DataCite (pending registration) |
From: Y.L. Chen [view email]
[v1]
Sat, 9 May 2026 09:03:54 UTC (2,474 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。