Multi-Agent Collaboration via Evolving Orchestration

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Dang, Yufan, Qian, Chen, Luo, Xueheng, Fan, Jingru, Xie, Zihao, Shi, Ruijie, Chen, Weize, Yang, Cheng, Che, Xiaoyin, Tian, Ye, Xiong, Xuantang, Han, Lei, Liu, Zhiyuan, Sun, Maosong
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915564808568832
author Dang, Yufan
Qian, Chen
Luo, Xueheng
Fan, Jingru
Xie, Zihao
Shi, Ruijie
Chen, Weize
Yang, Cheng
Che, Xiaoyin
Tian, Ye
Xiong, Xuantang
Han, Lei
Liu, Zhiyuan
Sun, Maosong
author_facet Dang, Yufan
Qian, Chen
Luo, Xueheng
Fan, Jingru
Xie, Zihao
Shi, Ruijie
Chen, Weize
Yang, Cheng
Che, Xiaoyin
Tian, Ye
Xiong, Xuantang
Han, Lei
Liu, Zhiyuan
Sun, Maosong
contents Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving. While recent research explores multi-agent collaboration among LLMs, most approaches rely on static organizational structures that struggle to adapt as task complexity and agent numbers grow, resulting in coordination overhead and inefficiencies. To this end, we propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a centralized orchestrator ("puppeteer") dynamically directs agents ("puppets") in response to evolving task states. This orchestrator is trained via reinforcement learning to adaptively sequence and prioritize agents, enabling flexible and evolvable collective reasoning. Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs. Analyses further reveal that the key improvements consistently stem from the emergence of more compact, cyclic reasoning structures under the orchestrator's evolution. Our code is available at https://github.com/OpenBMB/ChatDev/tree/puppeteer.
format Preprint
id arxiv_https___arxiv_org_abs_2505_19591
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Multi-Agent Collaboration via Evolving Orchestration
Dang, Yufan
Qian, Chen
Luo, Xueheng
Fan, Jingru
Xie, Zihao
Shi, Ruijie
Chen, Weize
Yang, Cheng
Che, Xiaoyin
Tian, Ye
Xiong, Xuantang
Han, Lei
Liu, Zhiyuan
Sun, Maosong
Computation and Language
Artificial Intelligence
Multiagent Systems
Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving. While recent research explores multi-agent collaboration among LLMs, most approaches rely on static organizational structures that struggle to adapt as task complexity and agent numbers grow, resulting in coordination overhead and inefficiencies. To this end, we propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a centralized orchestrator ("puppeteer") dynamically directs agents ("puppets") in response to evolving task states. This orchestrator is trained via reinforcement learning to adaptively sequence and prioritize agents, enabling flexible and evolvable collective reasoning. Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs. Analyses further reveal that the key improvements consistently stem from the emergence of more compact, cyclic reasoning structures under the orchestrator's evolution. Our code is available at https://github.com/OpenBMB/ChatDev/tree/puppeteer.
title Multi-Agent Collaboration via Evolving Orchestration
topic Computation and Language
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2505.19591