Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Towards Semantic-based Agent Communication Networks: Vision, Technologies, and Challenges

Ping Zhang, Rui Meng, Xiaodong Xu, Yaheng Wang, Zixuan Huang, Yiming Liu, Ruichen Zhang, Yinqiu Liu, Haonan Tong, Huishi Song, Gang Wu, Zhaoming Lu, Jiawen Kang, Geng Sun, Qinghe Du, Zhaohui Yang, Jingxuan Zhang, Han Meng, Lexi Xu, Haitao Zhao, Zesong Fei, Yiqing Zhou, Pei Xiao, Meixia Tao, Qinyu Zhang, Shuguang Cui, Rahim Tafazolli

Abstract

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.

Towards Semantic-based Agent Communication Networks: Vision, Technologies, and Challenges

Abstract

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.

Paper Structure

This paper contains 140 sections, 15 figures, 11 tables.

Table of Contents

  1. Introduction
  2. Motivation
  3. Preliminaries and State-of-the-Art Works
  4. Semantic Communications
  5. Agentic AI Systems
  6. Key Contributions and Outline
  7. Outline the Architecture of Semantic-based Agent Communication Networks
  8. Explore the State-of-the-Art in Semantic-based Agent Communication Networks
  9. Discuss Challenges and Potential Solutions
  10. Proposed Semantic-based Agent Communication Network Architecture
  11. Three Wireless Agent Network Layers
  12. Four AI Agent Entities
  13. Four Operational Stages for Semantic-enhanced Agentic AI Systems
  14. Semantic-based Wireless Agent Networks
  15. Intention Extraction and Understanding Layer
  16. ...and 125 more sections

Figures (15)

  • Figure 1: The evolution from 1G to 6G.
  • Figure 2: The structure of this paper.
  • Figure 3: The proposed architecture for semantic-based agent communication networks, comprising three layers, four entities, and four stages.
  • Figure 4: Illustration of the continuous goal recognition framework su2023fast, consisting of the attention, retention, motivation, and recognition stages for capturing relevant actions, retaining skill traces and representations, triggering recognition, and inferring goals.
  • Figure 5: Illustration of the ToM reasoner for partner intention modelling li2025theory, consisting of information extraction, ToM reasoning, and partner reasoning stages for constructing structured prompts, generating ToM reasoning, and inferring partner intention representations.
  • ...and 10 more figures