Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.24328v1</id>\n    <title>Towards Semantic-based Agent Communication Networks: Vision, Technologies, and Challenges</title>\n    <updated>2026-03-25T14:10:09Z</updated>\n    <link href='https://arxiv.org/abs/2603.24328v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.24328v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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 ca-pabilities in multi-modal environmental sensing, complex task coordination, and continuous self-optimization, is anticipated to drive the evolution toward agent-based communication net-works. 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 technologi-cal 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 collabora-tion 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 en-hance agent communication networks. Finally, we identify key challenges and present potential solutions to offer directional guidance for future research in this emerging field.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.SP'/>\n    <published>2026-03-25T14:10:09Z</published>\n    <arxiv:comment>46 pages, 15 figures</arxiv:comment>\n    <arxiv:primary_category term='eess.SP'/>\n    <author>\n      <name>Ping Zhang</name>\n    </author>\n    <author>\n      <name>Rui Meng</name>\n    </author>\n    <author>\n      <name>Xiaodong Xu</name>\n    </author>\n    <author>\n      <name>Yaheng Wang</name>\n    </author>\n    <author>\n      <name>Zixuan Huang</name>\n    </author>\n    <author>\n      <name>Yiming Liu</name>\n    </author>\n    <author>\n      <name>Ruichen Zhang</name>\n    </author>\n    <author>\n      <name>Yinqiu Liu</name>\n    </author>\n    <author>\n      <name>Haonan Tong</name>\n    </author>\n    <author>\n      <name>Huishi Song</name>\n    </author>\n    <author>\n      <name>Gang Wu</name>\n    </author>\n    <author>\n      <name>Zhaoming Lu</name>\n    </author>\n    <author>\n      <name>Jiawen Kang</name>\n    </author>\n    <author>\n      <name>Geng Sun</name>\n    </author>\n    <author>\n      <name>Qinghe Du</name>\n    </author>\n    <author>\n      <name>Zhaohui Yang</name>\n    </author>\n    <author>\n      <name>Jingxuan Zhang</name>\n    </author>\n    <author>\n      <name>Han Meng</name>\n    </author>\n    <author>\n      <name>Lexi Xu</name>\n    </author>\n    <author>\n      <name>Haitao Zhao</name>\n    </author>\n    <author>\n      <name>Zesong Fei</name>\n    </author>\n    <author>\n      <name>Yiqing Zhou</name>\n    </author>\n    <author>\n      <name>Pei Xiao</name>\n    </author>\n    <author>\n      <name>Meixia Tao</name>\n    </author>\n    <author>\n      <name>Qinyu Zhang</name>\n    </author>\n    <author>\n      <name>Shuguang Cui</name>\n    </author>\n    <author>\n      <name>Rahim Tafazolli</name>\n    </author>\n  </entry>"
}