Vision-Language-Action Models Meet World Models: Embodied Agentic AI for Low-Altitude Wireless Networks
For UAV-based wireless networks, this work provides a novel framework that enhances autonomous decision-making and closed-loop optimization, though it is an incremental step combining existing VLA and WM concepts.
This paper addresses challenges in deploying large generative models for low-altitude wireless networks by proposing an embodied agentic UAV framework that integrates a Vision-Language-Action model with a World Model, achieving robust, predictive, and sustainable autonomous control in complex dynamic environments.
Low-Altitude Wireless Networks (LAWNs), composed of Unmanned Aerial Vehicles (UAVs) and other aerial platforms, provide integrated perception, communication, and computation services in low-altitude airspace. However, deploying large generative models in this domain faces three major challenges: 1) Limited embodied action mapping; 2) Inadequate physical environment modeling; 3) Insufficient closed-loop optimization. To address these challenges, this study proposes an Embodied Agentic UAV framework. Centered on a Vision-Language-Action (VLA) model as the execution core, the framework establishes an end-to-end embodied decision-making pipeline from multimodal environmental perception to continuous control generation. In addition, a World Model (WM) is introduced to capture the coupling between UAV actions and environmental state evolution, thereby supporting environment prediction, policy verification, and dynamic optimization. Furthermore, memory and reflection mechanisms are incorporated to form an adaptive closed-loop optimization paradigm of decision, execution, evaluation, and update, thereby enhancing the system's autonomous decision-making capability and continual evolution ability in complex dynamic environments. Experimental results validate its effectiveness in enabling robust, predictive, and sustainable autonomous control in LAWNs.