Multi-Agent Coordination across Diverse Applications: A Survey

2025-02-20

AI Summary

This paper addresses the lack of a unified theoretical framework and practical guidelines for cross-domain collaboration in multi-agent systems (MAS). We propose a systematic review methodology structured around four fundamental questions: “What is collaboration?”, “Why collaborate?”, “With whom to collaborate?”, and “How to collaborate?”. Through systematic literature review, cross-domain paradigm mapping, and problem-driven classification, we establish the first comprehensive collaborative analysis framework covering seven application domains: search-and-rescue, logistics, transportation, humanoid robotics, satellite networks, and LLM-driven MAS. Our contributions include identifying three emerging research directions—hierarchical decentralized collaboration fusion, human-MAS collaboration, and LLM-empowered MAS—as well as revealing three persistent challenges: heterogeneity, scalability, and adaptive learning. The work clarifies foundational collaboration theories and establishes a cross-application comparative taxonomy of collaborative methods, thereby providing theoretical foundations and implementation pathways for MAS standardization and large-scale deployment.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Intelligent Robots: Multi-Robot Systems
• Cognitive Modeling & Cognitive Systems: Agent Architectures

Application Category

• Search and Retrieval-Augmented AI: Vertical and domain-specific search
• Systems and Infrastructure for Web, Mobile and WoT: Web applications in cross-disciplinary domains and verticals such as mixed reality, smart cities, and digital health
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Multi-agent coordination studies the underlying mechanism enabling the trending spread of diverse multi-agent systems (MAS) and has received increasing attention, driven by the expansion of emerging applications and rapid AI advances. This survey outlines the current state of coordination research across applications through a unified understanding that answers four fundamental coordination questions: (1) what is coordination; (2) why coordination; (3) who to coordinate with; and (4) how to coordinate. Our purpose is to explore existing ideas and expertise in coordination and their connections across diverse applications, while identifying and highlighting emerging and promising research directions. First, general coordination problems that are essential to varied applications are identified and analyzed. Second, a number of MAS applications are surveyed, ranging from widely studied domains, e.g., search and rescue, warehouse automation and logistics, and transportation systems, to emerging fields including humanoid and anthropomorphic robots, satellite systems, and large language models (LLMs). Finally, open challenges about the scalability, heterogeneity, and learning mechanisms of MAS are analyzed and discussed. In particular, we identify the hybridization of hierarchical and decentralized coordination, human-MAS coordination, and LLM-based MAS as promising future directions.

Problem

• Understanding multi-agent coordination mechanisms
• Exploring coordination across diverse applications
• Addressing scalability and heterogeneity in MAS

Innovation

• Multi-agent systems coordination
• Hierarchical decentralized hybrid models
• Large language models integration