Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Xu, Baixuan, Li, Chunyang, Wang, Weiqi, Fan, Wei, Zheng, Tianshi, Shi, Haochen, Fan, Tao, Song, Yangqiu, Yang, Qiang
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866908366603812864
author Xu, Baixuan
Li, Chunyang
Wang, Weiqi
Fan, Wei
Zheng, Tianshi
Shi, Haochen
Fan, Tao
Song, Yangqiu
Yang, Qiang
author_facet Xu, Baixuan
Li, Chunyang
Wang, Weiqi
Fan, Wei
Zheng, Tianshi
Shi, Haochen
Fan, Tao
Song, Yangqiu
Yang, Qiang
contents Designing effective collaboration structure for multi-agent LLM systems to enhance collective reasoning is crucial yet remains under-explored. In this paper, we systematically investigate how collaborative reasoning performance is affected by three key design dimensions: (1) Expertise-Domain Alignment, (2) Collaboration Paradigm (structured workflow vs. diversity-driven integration), and (3) System Scale. Our findings reveal that expertise alignment benefits are highly domain-contingent, proving most effective for contextual reasoning tasks. Furthermore, collaboration focused on integrating diverse knowledge consistently outperforms rigid task decomposition. Finally, we empirically explore the impact of scaling the multi-agent system with expertise specialization and study the computational trade off, highlighting the need for more efficient communication protocol design. This work provides concrete guidelines for configuring specialized multi-agent system and identifies critical architectural trade-offs and bottlenecks for scalable multi-agent reasoning. The code will be made available upon acceptance.
format Preprint
id arxiv_https___arxiv_org_abs_2505_07313
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study
Xu, Baixuan
Li, Chunyang
Wang, Weiqi
Fan, Wei
Zheng, Tianshi
Shi, Haochen
Fan, Tao
Song, Yangqiu
Yang, Qiang
Computation and Language
Artificial Intelligence
Designing effective collaboration structure for multi-agent LLM systems to enhance collective reasoning is crucial yet remains under-explored. In this paper, we systematically investigate how collaborative reasoning performance is affected by three key design dimensions: (1) Expertise-Domain Alignment, (2) Collaboration Paradigm (structured workflow vs. diversity-driven integration), and (3) System Scale. Our findings reveal that expertise alignment benefits are highly domain-contingent, proving most effective for contextual reasoning tasks. Furthermore, collaboration focused on integrating diverse knowledge consistently outperforms rigid task decomposition. Finally, we empirically explore the impact of scaling the multi-agent system with expertise specialization and study the computational trade off, highlighting the need for more efficient communication protocol design. This work provides concrete guidelines for configuring specialized multi-agent system and identifies critical architectural trade-offs and bottlenecks for scalable multi-agent reasoning. The code will be made available upon acceptance.
title Towards Multi-Agent Reasoning Systems for Collaborative Expertise Delegation: An Exploratory Design Study
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2505.07313