Towards semantic-based agent communication networks: vision, technologies, and challenges
Science China Information Sciences · 2026-10 · 69 (10)
DOI: 10.1007/s11432-026-5054-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science China Information Sciences, online erschienen am 24.09.2026. Verfasst von Ping Zhang und 26 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 214 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
The International Telecommunication Union (ITU) identifies “artificial intelligence (AI) and communication” as one of six key usage scenarios for 6G. Agentic AI, characterized by its capabilities in multi-modal environmental sensing, complex task coordination, and continuous self-optimization, is anticipated to drive the evolution toward agent-based communication networks. Semantic communication (SemCom), in turn, has emerged as a transformative paradigm that offers task-oriented efficiency, enhanced reliability in complex environments, and dynamic adaptation in resource allocation. However, comprehensive reviews that trace their technological evolution in the contexts of agent communications remain scarce. Addressing this gap, this paper systematically explores the role of semantics in agent communication networks. We first propose a novel architecture for semantic-based agent communication networks, structured into three layers, four entities, and four stages. Three wireless agent network layers define the logical structure and organization of entity interactions: the intention extraction and understanding layer, the semantic encoding and processing layer, and the distributed autonomy and collaboration layer. Across these layers, four AI agent entities, namely embodied agents, communication agents, network agents, and application agents, coexist and perform distinct tasks. Furthermore, four operational stages of semantic-enhanced agentic AI systems, namely perception, memory, reasoning, and action, form a cognitive cycle guiding agent behavior. Based on the proposed architecture, we provide a comprehensive review of the state-of-the-art on how semantics enhance agent communication networks. Finally, we identify key challenges and present potential solutions to offer directional guidance for future research in this emerging field.
Zitieren
APA
Zhang, P., Meng, R., Xu, X., Wang, Y., Huang, Z., Liu, Y., Zhang, R., Liu, Y., Tong, H., Song, H., Wu, G., Lu, Z., Kang, J., Sun, G., Du, Q., Yang, Z., Zhang, J., Meng, H., Xu, L., …, & Tafazolli, R. (2026). Towards semantic-based agent communication networks: vision, technologies, and challenges. Science China Information Sciences, 69(10). https://doi.org/10.1007/s11432-026-5054-3
Vancouver
Zhang P, Meng R, Xu X, Wang Y, Huang Z, Liu Y, et al. Towards semantic-based agent communication networks: vision, technologies, and challenges. Science China Information Sciences. 2026;69(10). doi:10.1007/s11432-026-5054-3
BibTeX
@article{Zhang2026,
author = {Zhang, Ping and Meng, Rui and Xu, Xiaodong and Wang, Yaheng and Huang, Zixuan and Liu, Yiming and Zhang, Ruichen and Liu, Yinqiu and Tong, Haonan and Song, Huishi and Wu, Gang and Lu, Zhaoming and Kang, Jiawen and Sun, Geng and Du, Qinghe and Yang, Zhaohui and Zhang, Jingxuan and Meng, Han and Xu, Lexi and Zhao, Haitao and Fei, Zesong and Zhou, Yiqing and Xiao, Pei and Tao, Meixia and Zhang, Qinyu and Cui, Shuguang and Tafazolli, Rahim},
title = {Towards semantic-based agent communication networks: vision, technologies, and challenges},
journal = {Science China Information Sciences},
year = {2026},
volume = {69},
number = {10},
doi = {10.1007/s11432-026-5054-3}
}
EUVIMED