Toward Goal-Oriented Communication in Multi-Agent Systems: An overview
For researchers in multi-agent systems, this paper provides a comprehensive overview of a growing field, but it is a survey without novel results.
This survey reviews goal-oriented communication in multi-agent systems, which prioritizes task-relevant information over traditional metrics like bandwidth. It bridges information theory, communication theory, and machine learning, covering foundational concepts, learning-based approaches, and applications in swarm robotics, federated learning, and edge computing.
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.