AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Zhexuan, Wang, Yutong, Liu, Xuebo, Ding, Liang, Zhang, Miao, Liu, Jie, Zhang, Min
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866908281423790080
author Wang, Zhexuan
Wang, Yutong
Liu, Xuebo
Ding, Liang
Zhang, Miao
Liu, Jie
Zhang, Min
author_facet Wang, Zhexuan
Wang, Yutong
Liu, Xuebo
Ding, Liang
Zhang, Miao
Liu, Jie
Zhang, Min
contents Multi-agent systems (MAS) based on large language models (LLMs) have demonstrated significant potential in collaborative problem-solving. However, they still face substantial challenges of low communication efficiency and suboptimal task performance, making the careful design of the agents' communication topologies particularly important. Inspired by the management theory that roles in an efficient team are often dynamically adjusted, we propose AgentDropout, which identifies redundant agents and communication across different communication rounds by optimizing the adjacency matrices of the communication graphs and eliminates them to enhance both token efficiency and task performance. Compared to state-of-the-art methods, AgentDropout achieves an average reduction of 21.6% in prompt token consumption and 18.4% in completion token consumption, along with a performance improvement of 1.14 on the tasks. Furthermore, the extended experiments demonstrate that AgentDropout achieves notable domain transferability and structure robustness, revealing its reliability and effectiveness. We release our code at https://github.com/wangzx1219/AgentDropout.
format Preprint
id arxiv_https___arxiv_org_abs_2503_18891
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration
Wang, Zhexuan
Wang, Yutong
Liu, Xuebo
Ding, Liang
Zhang, Miao
Liu, Jie
Zhang, Min
Computation and Language
Artificial Intelligence
Multi-agent systems (MAS) based on large language models (LLMs) have demonstrated significant potential in collaborative problem-solving. However, they still face substantial challenges of low communication efficiency and suboptimal task performance, making the careful design of the agents' communication topologies particularly important. Inspired by the management theory that roles in an efficient team are often dynamically adjusted, we propose AgentDropout, which identifies redundant agents and communication across different communication rounds by optimizing the adjacency matrices of the communication graphs and eliminates them to enhance both token efficiency and task performance. Compared to state-of-the-art methods, AgentDropout achieves an average reduction of 21.6% in prompt token consumption and 18.4% in completion token consumption, along with a performance improvement of 1.14 on the tasks. Furthermore, the extended experiments demonstrate that AgentDropout achieves notable domain transferability and structure robustness, revealing its reliability and effectiveness. We release our code at https://github.com/wangzx1219/AgentDropout.
title AgentDropout: Dynamic Agent Elimination for Token-Efficient and High-Performance LLM-Based Multi-Agent Collaboration
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2503.18891