arXiv cs.AI· Zheng Lin, Zhanwei Wang, Yuxin Zhang, Yafei Wang, Ons Aouedi, Zihan Fang, Jinfeng Xu, Jing Yang, Vu Nguyen Ha, Yuanwei Liu, Mohamed-Slim Alouini, Symeon Chatzinotas·· 14 小时前AI 评分31
卫星智能：LEO 星座中的分布式训练、协同推理与 LLM 适配
Satellite Intelligence: Distributed Training, Collaborative Inference,and LLM Adaptation in LEO Constellation
AI 导读
一篇综述首次将 LEO 卫星网络中的分布式训练、协同推理与在轨 LLM 适配服务三者统一纳入讨论，此前相关综述均只单独考察其中某一方面。文章提出约束感知的设计原则，梳理了联邦学习与拆分学习支撑的星地协同训练、单星/多星/星地三类协同推理架构，以及在 SWaP 受限条件下部署和资源感知服务 LLM 的前沿挑战。
正文 · 原文
Authors:Zheng Lin, Zhanwei Wang, Yuxin Zhang, Yafei Wang, Ons Aouedi, Zihan Fang, Jinfeng Xu, Jing Yang, Vu Nguyen Ha, Yuanwei Liu, Mohamed-Slim Alouini, Symeon Chatzinotas
Abstract:The proliferation of orbital sensing data and the real-time demands of emerging global services are pushing low Earth orbit (LEO) satellite networks from bent-pipe relays toward intelligent onboard processing. This shift confronts a fundamental tension, where modern artificial intelligence (AI) training paradigms require intensive computation, abundant memory, and stable connectivity, all of which are scarce under the dynamic topologies, intermittent links, and severe size, weight, and power (SWaP) constraints of satellite networks. Addressing this tension demands rethinking AI workflows, from training and inference to the emerging deployment of large language models (LLMs), under a constraint-aware design philosophy. To the best of our knowledge, this paper provides the first survey that jointly covers all three, whereas prior surveys examine these aspects in isolation. We begin by identifying the deployment challenge of satellite intelligence (SI) and deriving design principles for SI. We then examine three advancing paradigms: i) distributed training, where federated learning (FL) and split learning (SL) enable satellite-ground co-training under resource limitations; ii) collaborative inference, which exploits single-satellite, multi-satellite, and satellite-ground architectures to meet real-time service demands; and iii) on-orbit LLM adaptation and serving, which tackles the frontier challenge of deploying LLMs under severe orbital constraints and resource-aware serving. Finally, we identify open challenges and future directions. By bridging the AI and satellite networks, this paper provides a research roadmap for the implementation of space-native AI technologies.
| Comments: | 38 pages, 16 figures |
| Subjects: | Networking and Internet Architecture (cs.NI); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.35282 [cs.NI] |
| (or arXiv:2610.35282v1 [cs.NI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.35282 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lin Zheng [view email]
[v1]
Mon, 26 Oct 2026 11:55:41 UTC (5,589 KB)
来源：arXiv cs.AI · arxiv.org