Agentic Satellite-Augmented Low-Altitude Economy and Terrestrial Networks: A Survey on Generative Approaches

TY - JOUR

T1 - Agentic Satellite-Augmented Low-Altitude Economy and Terrestrial Networks

T2 - A Survey on Generative Approaches

AU - Gao, Xiaozheng

AU - Wang, Yichen

AU - Liu, Bosen

AU - Zhou, Xiao

AU - Zhang, Ruichen

AU - Wang, Jiacheng

AU - Niyato, Dusit

AU - In Kim, Dong

AU - Jamalipour, Abbas

AU - Yuen, Chau

AU - An, Jianping

AU - Yang, Kai

N1 - Publisher Copyright: © 1998-2012 IEEE.

PY - 2026

Y1 - 2026

N2 - The development of satellite-augmented low-altitude economy and terrestrial networks (SLAETNs) demands intelligent and autonomous systems that can operate reliably across heterogeneous, dynamic, and mission-critical environments. To address these challenges, this article surveys the state-of-the-art literature on enabling agentic artificial intelligence (AI), that is, artificial agents capable of perceiving, reasoning, and acting, through the application of generative AI (GAI) and large language models (LLMs) in SLAETNs. We begin by introducing the architecture and characteristics of SLAETNs, analyzing the challenges that arise in integrating satellite, aerial, and terrestrial components. Then, we present a model-driven foundation by systematically reviewing five major categories of generative models: variational autoencoders (VAEs), generative adversarial networks (GANs), generative diffusion models (GDMs), transformer-based models (TBMs), and LLMs. Moreover, we discuss critical deployment strategies and propose a conceptual framework for deploying agentic AI in SLAETNs. Building on this foundation, we examine how these models empower agentic functions across three domains: communication enhancement, security and privacy protection, and intelligent satellite tasks. Moreover, we present a comprehensive guide to open-source frameworks, datasets, and simulation platforms, and deliver a case study on agentic network optimization in SLAETN scenarios. Finally, we outline key future directions for building scalable, adaptive, and trustworthy generative agents in SLAETNs. This survey aims to provide a unified understanding and actionable reference for advancing agentic AI in next-generation networks.

AB - The development of satellite-augmented low-altitude economy and terrestrial networks (SLAETNs) demands intelligent and autonomous systems that can operate reliably across heterogeneous, dynamic, and mission-critical environments. To address these challenges, this article surveys the state-of-the-art literature on enabling agentic artificial intelligence (AI), that is, artificial agents capable of perceiving, reasoning, and acting, through the application of generative AI (GAI) and large language models (LLMs) in SLAETNs. We begin by introducing the architecture and characteristics of SLAETNs, analyzing the challenges that arise in integrating satellite, aerial, and terrestrial components. Then, we present a model-driven foundation by systematically reviewing five major categories of generative models: variational autoencoders (VAEs), generative adversarial networks (GANs), generative diffusion models (GDMs), transformer-based models (TBMs), and LLMs. Moreover, we discuss critical deployment strategies and propose a conceptual framework for deploying agentic AI in SLAETNs. Building on this foundation, we examine how these models empower agentic functions across three domains: communication enhancement, security and privacy protection, and intelligent satellite tasks. Moreover, we present a comprehensive guide to open-source frameworks, datasets, and simulation platforms, and deliver a case study on agentic network optimization in SLAETN scenarios. Finally, we outline key future directions for building scalable, adaptive, and trustworthy generative agents in SLAETNs. This survey aims to provide a unified understanding and actionable reference for advancing agentic AI in next-generation networks.

KW - Satellite-augmented low-altitude economy and terrestrial networks

KW - agentic AI

KW - generative AI

KW - large language models

UR - https://www.scopus.com/pages/publications/105029370019

U2 - 10.1109/COMST.2026.3660854

DO - 10.1109/COMST.2026.3660854

M3 - Review article

AN - SCOPUS:105029370019

SN - 1553-877X

VL - 28

SP - 4800

EP - 4841

JO - IEEE Communications Surveys and Tutorials

JF - IEEE Communications Surveys and Tutorials

ER -