Saved in:
Bibliographic Details
Main Authors: Wang, Zixiang, Gong, Mengjia, Sun, Qiyu, Xu, Jing, Mao, Shuai, Jin, Xin, Han, Qing-Long, Tang, Yang
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.18133
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908980045938688
author Wang, Zixiang
Gong, Mengjia
Sun, Qiyu
Xu, Jing
Mao, Shuai
Jin, Xin
Han, Qing-Long
Tang, Yang
author_facet Wang, Zixiang
Gong, Mengjia
Sun, Qiyu
Xu, Jing
Mao, Shuai
Jin, Xin
Han, Qing-Long
Tang, Yang
contents With the rapid advancement of artificial intelligence, multi-agent systems (MASs) are evolving from classical paradigms toward architectures built upon large foundation models (LFMs). This survey provides a systematic review and comparative analysis of classical MASs (CMASs) and LFM-based MASs (LMASs). First, within a closed-loop coordination framework, CMASs are reviewed across four fundamental dimensions: perception, communication, decision-making, and control. Beyond this framework, LMASs integrate LFMs to lift collaboration from low-level state exchanges to semantic-level reasoning, enabling more flexible coordination and improved adaptability across diverse scenarios. Then, a comparative analysis is conducted to contrast CMASs and LMASs across architecture, operating mechanism, adaptability, and application. Finally, future perspectives on MASs are presented, summarizing open challenges and potential research opportunities.
format Preprint
id arxiv_https___arxiv_org_abs_2604_18133
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures
Wang, Zixiang
Gong, Mengjia
Sun, Qiyu
Xu, Jing
Mao, Shuai
Jin, Xin
Han, Qing-Long
Tang, Yang
Artificial Intelligence
With the rapid advancement of artificial intelligence, multi-agent systems (MASs) are evolving from classical paradigms toward architectures built upon large foundation models (LFMs). This survey provides a systematic review and comparative analysis of classical MASs (CMASs) and LFM-based MASs (LMASs). First, within a closed-loop coordination framework, CMASs are reviewed across four fundamental dimensions: perception, communication, decision-making, and control. Beyond this framework, LMASs integrate LFMs to lift collaboration from low-level state exchanges to semantic-level reasoning, enabling more flexible coordination and improved adaptability across diverse scenarios. Then, a comparative analysis is conducted to contrast CMASs and LMASs across architecture, operating mechanism, adaptability, and application. Finally, future perspectives on MASs are presented, summarizing open challenges and potential research opportunities.
title Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures
topic Artificial Intelligence
url https://arxiv.org/abs/2604.18133