Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures
For researchers and practitioners in multi-agent systems, this survey provides a structured comparison and identifies open challenges, but it is an incremental survey without novel results.
This survey systematically reviews and compares classical multi-agent systems (CMASs) with large foundation model-based MASs (LMASs), showing that LMASs enable more flexible coordination and improved adaptability by lifting collaboration from low-level state exchanges to semantic-level reasoning.
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.