Toward Goal-Oriented Communication in Multi-Agent Systems: An overview

TL;DR

This paper surveys goal-oriented communication strategies in multi-agent systems, emphasizing task relevance over message fidelity, and explores foundational theories, learning approaches, and applications in various domains.

Contribution

It provides a comprehensive overview of goal-oriented communication in MAS, integrating perspectives from multiple fields and highlighting open challenges and future directions.

Findings

Emphasizes importance of task-relevant information in MAS communication

Reviews learning-based approaches and emergent protocols

Discusses applications in swarm robotics, federated learning, edge computing

Abstract

As multi-agent systems (MAS) become increasingly prevalent in autonomous systems, distributed control, and edge intelligence, efficient communication under resource constraints has emerged as a critical challenge. Traditional communication paradigms often emphasize message fidelity or bandwidth optimization, overlooking the task relevance of the exchanged information. In contrast, goal-oriented communication prioritizes the importance of information with respect to the agents' shared objectives. This review provides a comprehensive survey of goal-oriented communication in MAS, bridging perspectives from information theory, communication theory, and machine learning. We examine foundational concepts alongside learning-based approaches and emergent protocols. Special attention is given to coordination under communication constraints, as well as applications in domains such as swarm robotics, federated learning, and edge computing. The paper concludes with a discussion of open challenges and future research directions at the intersection of communication theory, machine learning, and multi-agent decision making.