Summary
Mobile networks are changing to focus more on machines and agents working on specific tasks rather than just carrying data between people. The authors present a new framework called Mobile Embodied Agent Network (MEAN) that combines sensing, communication, computing, decision-making, and actions into one system designed to complete tasks in a loop. They explain how large AI models help understand tasks, token communication lets agents share meaning, and reinforcement learning helps the system improve over time based on feedback. This framework also discusses how new technologies can work together with MEAN to improve networks focused on task-oriented activities.
What this means in practice
- •For network engineers: Design mobile networks that prioritize task completion using integrated sensing, AI, and communication techniques.
- •For robotics developers: Build multi-agent robotic systems that communicate and adapt through shared intelligence and feedback loops enabled by MEAN.
A survey. It maps existing work.
Authors
Zhaoyang Zhang, Lingxiao Sun, Weijie Zhou, Chunhui Feng, Zhaohui Yang, Xuan Cheng, Tianyi Qin, Zhixian Kong, Baoping Cheng, Zijian Wu, Jingze Che
Abstract
Mobile networks are evolving from human-centered, data-oriented communication infrastructures toward machine- and/or agent-dominant, task-oriented platforms that are to serve the rapidly increasing networked machines and embodied agents. In order to fulfill the newly arose complex task objectives, the framework of future mobile network is to be innovated to reflect and facilitate the intrinsic interplay and integration of the underlying processes of perception, communication, computation, decision, action, and feedback, etc. This survey establishes the mobile embodied agent network (MEAN) as a task-oriented networking paradigm in which networking and distributed intelligence are jointly organized around closed-loop embodied task execution. We first establish a unified MEAN framework that explains how network resources and intelligent functions jointly support embodied task execution, and extend its performance indicators from conventional communication metrics to embodied task outcomes and cross-layer system effects. With this framework, we analyze three complementary enabling mechanisms that form a cognition-interaction-adaption loop. Large artificial intelligence (AI) models provide high-level cognition, token communication connects this cognition with distributed agents through shared semantic representations, and reinforcement learning closes the loop by adapting system operation to network, task, and physical feedback. We further investigate the bidirectional interplay between MEAN and emerging technologies, showing how they mutually extend system capabilities and reshape task-oriented network design. Finally, we discuss open challenges and future research directions toward the practical realization of MEAN over real joint communication and computation platform.