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.
@article{arxiv.2604.18133,
title = {Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures},
author = {Zixiang Wang and Mengjia Gong and Qiyu Sun and Jing Xu and Shuai Mao and Xin Jin and Qing-Long Han and Yang Tang},
journal= {arXiv preprint arXiv:2604.18133},
year = {2026}
}