With the advent of mobile networks, we are witnessing an unprecedented shift in the landscape of mobile network services, evolving from traditional voice calls to advanced artificial intelligence (AI) services. This paper delves into the intricacies of this evolution, particularly emphasizing the deep integration of AI agents into 6G networks. Despite recent researches in using large language model (LLM) and AI agent for network automation, the fundamental mobile AI agent use cases, their network requirements, potential network architecture and enabling technologies for supporting the pervasive AI agents in 6G era are largely unexplored. In this article, we present an in-depth analysis of typical mobile AI agent use cases in 6G, consisting of AI agent-based 6G network automation, handheld personalized agents, connected robotics and autonomous systems, and wearable AI agent. Then, we elucidate a novel system architecture that supports identified use cases. The article also addresses core aspects of enabling technologies, including 6G agent and application agent collaboration, efficient model and memory management, coordinated agent-to-agent communication and support of multi-modal data transmission. A proof of concept prototype is also presented to demonstrate 6G agent and application AI agent collaboration. Finally, three challenges and research directions: energy saving, security protection and AI agent tailored communication are discussed. This article lays a foundation for understanding the role of 6G in realizing the full potential of AI agents in various applications.

中文翻译：

---

赋能6G时代移动AI Agent：架构与关键技术


随着移动网络的出现，我们正在目睹移动网络服务格局发生前所未有的转变，从传统的语音通话演变为先进的人工智能（AI）服务。本文深入探讨了这一演变的复杂性，特别强调了人工智能代理与 6G 网络的深度集成。尽管最近有关于使用大语言模型 ( LLM ) 和 AI 代理进行网络自动化的研究，但基本的移动 AI 代理用例、其网络要求、潜在的网络架构以及支持 6G 时代普遍的 AI 代理的支持技术在很大程度上尚未得到探索。在本文中，我们深入分析了 6G 中典型的移动人工智能代理用例，包括基于人工智能代理的 6G 网络自动化、手持式个性化代理、互联机器人和自主系统以及可穿戴人工智能代理。然后，我们阐明了一种支持已确定用例的新颖系统架构。本文还讨论了支持技术的核心方面，包括 6G 代理和应用程序代理协作、高效模型和内存管理、协调的代理间通信以及对多模式数据传输的支持。还提供了概念验证原型来演示 6G 代理和应用程序 AI 代理协作。最后讨论了节能、安全防护和AI代理定制通信三个挑战和研究方向。本文为理解 6G 在充分发挥人工智能代理在各种应用中的潜力方面的作用奠定了基础。