Toward Goal-Oriented Communication in Multi-Agent Systems: An Overview
2026 (English)In: IEEE Open Journal of the Communications Society, E-ISSN 2644-125X, Vol. 7, p. 6576-6611Article in journal (Refereed) Published
Abstract [en]
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.
Place, publisher, year, edition, pages
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC , 2026. Vol. 7, p. 6576-6611
Keywords [en]
Modeling; Learning (artificial intelligence); Measurement; Optimization; Aging; Timing; Design methodology; Rate-distortion; Image sensors; Distortion; Goal-oriented communication; multi-agent systems; communication efficiency; coordination under constraints
National Category
Computer Engineering
Identifiers
URN: urn:nbn:se:liu:diva-225891DOI: 10.1109/OJCOMS.2026.3703748ISI: 001797680900006OAI: oai:DiVA.org:liu-225891DiVA, id: diva2:2082593
Note
Funding Agencies|LEArning-Driven and Evolved Radio for 6G Communication Systems (6G-LEADER), Smart Networks and Services Joint Undertaking (SNS JU) through the European Union's Horizon Europe Research and Innovation Program [101192080]; Emerging Cooperative Autonomous Systems: Information for Control and Estimation (MINERVA), European Research Council (ERC) - European Union's Horizon 2022 Research and Innovation Program [101044629]; Swedish Research Council (VR); Excellence Center at Linkoping-Lund in Information Technology (ELLIIT) [101192080]; Business Finland 6G-BRIDGE Program
2026-07-012026-07-012026-08-22