Scaling Large Language Model-based Multi-Agent Collaboration

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Qian, Chen, Xie, Zihao, Wang, YiFei, Liu, Wei, Zhu, Kunlun, Xia, Hanchen, Dang, Yufan, Du, Zhuoyun, Chen, Weize, Yang, Cheng, Liu, Zhiyuan, Sun, Maosong
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866909538016296960
author Qian, Chen
Xie, Zihao
Wang, YiFei
Liu, Wei
Zhu, Kunlun
Xia, Hanchen
Dang, Yufan
Du, Zhuoyun
Chen, Weize
Yang, Cheng
Liu, Zhiyuan
Sun, Maosong
author_facet Qian, Chen
Xie, Zihao
Wang, YiFei
Liu, Wei
Zhu, Kunlun
Xia, Hanchen
Dang, Yufan
Du, Zhuoyun
Chen, Weize
Yang, Cheng
Liu, Zhiyuan
Sun, Maosong
contents Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning. Inspired by the neural scaling law--increasing neurons enhances performance, this study explores whether the continuous addition of collaborative agents can yield similar benefits. Technically, we utilize directed acyclic graphs to organize agents into a multi-agent collaboration network (MacNet), upon which their interactive reasoning is topologically orchestrated for autonomous task solving. Extensive evaluations reveal that it effectively supports collaboration among over a thousand agents, with irregular topologies outperforming regular ones. We also identify a collaborative scaling law--the overall performance follows a logistic growth pattern as agents scale, with collaborative emergence occurring earlier than traditional neural emergence. We speculate this may be because scaling agents catalyzes their multidimensional considerations during interactive reflection and refinement, thereby producing more comprehensive artifacts. The code is available at https://github.com/OpenBMB/ChatDev/tree/macnet.
format Preprint
id arxiv_https___arxiv_org_abs_2406_07155
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Scaling Large Language Model-based Multi-Agent Collaboration
Qian, Chen
Xie, Zihao
Wang, YiFei
Liu, Wei
Zhu, Kunlun
Xia, Hanchen
Dang, Yufan
Du, Zhuoyun
Chen, Weize
Yang, Cheng
Liu, Zhiyuan
Sun, Maosong
Artificial Intelligence
Computation and Language
Multiagent Systems
Networking and Internet Architecture
Social and Information Networks
Recent breakthroughs in large language model-driven autonomous agents have revealed that multi-agent collaboration often surpasses each individual through collective reasoning. Inspired by the neural scaling law--increasing neurons enhances performance, this study explores whether the continuous addition of collaborative agents can yield similar benefits. Technically, we utilize directed acyclic graphs to organize agents into a multi-agent collaboration network (MacNet), upon which their interactive reasoning is topologically orchestrated for autonomous task solving. Extensive evaluations reveal that it effectively supports collaboration among over a thousand agents, with irregular topologies outperforming regular ones. We also identify a collaborative scaling law--the overall performance follows a logistic growth pattern as agents scale, with collaborative emergence occurring earlier than traditional neural emergence. We speculate this may be because scaling agents catalyzes their multidimensional considerations during interactive reflection and refinement, thereby producing more comprehensive artifacts. The code is available at https://github.com/OpenBMB/ChatDev/tree/macnet.
title Scaling Large Language Model-based Multi-Agent Collaboration
topic Artificial Intelligence
Computation and Language
Multiagent Systems
Networking and Internet Architecture
Social and Information Networks
url https://arxiv.org/abs/2406.07155