Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures

TL;DR

This survey compares classical multi-agent systems with large foundation model-based systems, highlighting their architectures, capabilities, and future research directions in AI coordination.

Contribution

It provides a systematic review and comparative analysis of classical and LFM-enabled multi-agent systems, emphasizing their differences and future challenges.

Findings

LFM-based MASs enable semantic-level reasoning for better coordination.

Comparison shows LMASs have higher adaptability and flexibility.

Future research faces open challenges in scalability and integration.

Abstract

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.