Saved in:
Bibliographic Details
Main Authors: Tian, Chunhao, Wang, Yutong, Liu, Xuebo, Wang, Zhexuan, Ding, Liang, Zhang, Miao, Zhang, Min
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.19236
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912601699516416
author Tian, Chunhao
Wang, Yutong
Liu, Xuebo
Wang, Zhexuan
Ding, Liang
Zhang, Miao
Zhang, Min
author_facet Tian, Chunhao
Wang, Yutong
Liu, Xuebo
Wang, Zhexuan
Ding, Liang
Zhang, Miao
Zhang, Min
contents Proper initialization is crucial for any system, particularly in multi-agent systems (MAS), where it plays a pivotal role in determining both the system's efficiency and effectiveness. However, existing MAS initialization methods do not fully account for the collaborative needs of the generated agents in subsequent stages. Inspired by the principles of effective team composition, we propose AgentInit, which aims to optimize the structure of agent teams. Specifically, in addition to multi-round interactions and reflections between agents during agent generation, AgentInit incorporates a Natural Language to Format mechanism to ensure consistency and standardization. Balanced team selection strategies using Pareto principles are subsequently applied to jointly consider agent team diversity and task relevance to promote effective and efficient collaboration and enhance overall system performance. Experiments show that AgentInit consistently outperforms state-of-the-art initialization methods and pre-defined strategies across various frameworks and tasks, achieving an overall performance improvement of up to 1.2 and 1.6, respectively, while also significantly reducing token consumption. Further analysis confirms its strong transferability to similar tasks and verifies the effectiveness of its key components, demonstrating its capability and adaptability as a reliable MAS initialization method. Source code and models are available at https://github.com/1737423697/AgentInit.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19236
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration
Tian, Chunhao
Wang, Yutong
Liu, Xuebo
Wang, Zhexuan
Ding, Liang
Zhang, Miao
Zhang, Min
Artificial Intelligence
Proper initialization is crucial for any system, particularly in multi-agent systems (MAS), where it plays a pivotal role in determining both the system's efficiency and effectiveness. However, existing MAS initialization methods do not fully account for the collaborative needs of the generated agents in subsequent stages. Inspired by the principles of effective team composition, we propose AgentInit, which aims to optimize the structure of agent teams. Specifically, in addition to multi-round interactions and reflections between agents during agent generation, AgentInit incorporates a Natural Language to Format mechanism to ensure consistency and standardization. Balanced team selection strategies using Pareto principles are subsequently applied to jointly consider agent team diversity and task relevance to promote effective and efficient collaboration and enhance overall system performance. Experiments show that AgentInit consistently outperforms state-of-the-art initialization methods and pre-defined strategies across various frameworks and tasks, achieving an overall performance improvement of up to 1.2 and 1.6, respectively, while also significantly reducing token consumption. Further analysis confirms its strong transferability to similar tasks and verifies the effectiveness of its key components, demonstrating its capability and adaptability as a reliable MAS initialization method. Source code and models are available at https://github.com/1737423697/AgentInit.
title AgentInit: Initializing LLM-based Multi-Agent Systems via Diversity and Expertise Orchestration for Effective and Efficient Collaboration
topic Artificial Intelligence
url https://arxiv.org/abs/2509.19236