Multi-Agent Collaboration Mechanisms: A Survey of LLMs

2025-01-10

AI Summary

Existing LLM-driven multi-agent collaboration research lacks a systematic, unified framework for modeling dynamic inter-agent relationships and structural principles underlying collective intelligence. Method: We propose the first comprehensive five-dimensional collaboration taxonomy—covering agents, interaction types, organizational structures, coordination strategies, and protocols—and explicitly model cooperative, competitive, and coetitive (cooperative-competitive) dynamics. Leveraging protocol-based collaboration modeling, structured framework design, and cross-domain empirical validation (5G/6G networks, Industry 5.0, question answering, and socio-cultural scenarios), we construct a knowledge graph spanning theory, architecture, and applications. Contribution/Results: Our work identifies decentralization and role-driven strategies as critical drivers of collective intelligence emergence; uncovers core challenges and frontiers in artificial collective intelligence; and establishes a reusable, principled methodology for collaborative AI systems—bridging theoretical rigor with practical deployability.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Game Theory and Economic Paradigms: Coordination and Collaboration

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work

Abstract

With recent advances in Large Language Models (LLMs), Agentic AI has become phenomenal in real-world applications, moving toward multiple LLM-based agents to perceive, learn, reason, and act collaboratively. These LLM-based Multi-Agent Systems (MASs) enable groups of intelligent agents to coordinate and solve complex tasks collectively at scale, transitioning from isolated models to collaboration-centric approaches. This work provides an extensive survey of the collaborative aspect of MASs and introduces an extensible framework to guide future research. Our framework characterizes collaboration mechanisms based on key dimensions: actors (agents involved), types (e.g., cooperation, competition, or coopetition), structures (e.g., peer-to-peer, centralized, or distributed), strategies (e.g., role-based or model-based), and coordination protocols. Through a review of existing methodologies, our findings serve as a foundation for demystifying and advancing LLM-based MASs toward more intelligent and collaborative solutions for complex, real-world use cases. In addition, various applications of MASs across diverse domains, including 5G/6G networks, Industry 5.0, question answering, and social and cultural settings, are also investigated, demonstrating their wider adoption and broader impacts. Finally, we identify key lessons learned, open challenges, and potential research directions of MASs towards artificial collective intelligence.

Problem

• Multi-Agent AI
• Complex Task Solving
• Teamwork Optimization

Innovation

• Collaborative AI Framework
• Enhanced Intelligence and Efficiency
• Broad Application Potential