← Back to all news
arXiv Machine Learning By Xin Ming Li, Peng Hu

RAMA: Retrieval-Augmented Multi-Agent Routing with Episodic Memory for LEO Satellite Networks

Read the original on arXiv Machine Learning →

RAMA is a retrieval‑augmented multi‑agent deep reinforcement learning framework for routing in Low‑Earth Orbit satellite networks. It combines each satellite’s local observation, recent routing history, neighboring state information, and retrieved entries from a per‑satellite episodic memory, integrating them via a Transformer‑based decision network trained with Approximate Information State objectives. In a 140‑satellite Kepler constellation, RAMA cuts mean end‑to‑end latency by 13.4% and 99th‑percentile latency by 66.7% compared to a state‑of‑the‑art DDQN, and on a 1,584‑satellite Starlink shell 1 it achieves a 93.2% mean latency reduction, with further gains from online updates.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 18

STR-Agent: An LLM-Driven Agent for QoS-Aware Routing in LEO Satellite Networks

STR-Agent is an LLM-driven framework designed for QoS-aware routing in Low Earth Orbit satellite networks. It integrates intent perception, tool-based execution, experience accumulation, and reflection-based policy adaptation to translate natural-language service requests into adaptive routing decisions. In simulations on a Walker-Delta constellation, STR-Agent reduces end-to-end delay by up to 60% compared with DQ-Dijkstra and improves intent-understanding accuracy from 45.4% to 92.45% after fine-tuning, with the Reflection Module providing additional delay reductions.

By Bowen Lu, Mugen Peng, Yaohua Sun, Hongyu Wang, Kerui Guo, Wenjia Xu
llmsagentsfine-tuning
More like this →
arXiv AI
Oct 27

Satellite Intelligence: Distributed Training, Collaborative Inference,and LLM Adaptation in LEO Constellation

arXiv:2610.35282v1 Announce Type: cross Abstract: The proliferation of orbital sensing data and the real-time demands of emerging global services are pushing low Earth orbit (LEO) satellite networks...

By 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
llms
More like this →
arXiv Machine Learning
Oct 28

From Human Intent to In-Orbit Action: A Self-Learning Large Language Model Agent for 6G Satellite Networks

The paper introduces ALMOND, a cognitive framework that bridges the gap between human intent and low‑level control logic for 6G low Earth orbit satellite networks. It employs a bidirectional semantic engine to convert natural‑language requests into multi‑objective reward functions and extracts operational constraints from failed reinforcement‑learning trajectories, while a large‑language‑model‑guided graph neuroevolution designs efficient policy architectures. In a 350‑satellite digital twin, ALMOND improves polar handover success from 55% to over 95%, speeds convergence threefold, and cuts reward‑engineering time from 48 to 4.5 hours, all within a compute‑frugal on‑board policy of under 50,000 parameters.

By Zhengqian Xu, Yasheng Zhang, Chenhua Sun, Shan Lu, Chengcheng Li
llmsagentsreinforcement-learning
More like this →
arXiv Machine Learning
Aug 5

FedRings: A Scalable and Topology-Aware Federated Learning Framework for LEO Satellite Constellations

arXiv:2608. 03436v1 Announce Type: cross Abstract: Federated learning over low Earth orbit (LEO) satellite networks is limited by frequent link changes, short contact times, and a highly dynamic topology, making centralized or synchronized training inefficient and hard to scale.

By Ziwu Liu, In\^es Pinto Gouveia, Rehana Yasmin, Paulo Esteves-Verissimo, Ali Shoker
More like this →
arXiv Machine Learning
Sep 18

Traffic Engineering in Large-scale Networks with Generalizable Graph Neural Networks

The paper introduces TELGEN, a traffic engineering algorithm that uses graph neural networks to predict an optimal TE algorithm rather than a direct solution. TELGEN generalizes across diverse network topologies and traffic patterns, achieving less than a 3% optimality gap on networks up to 5,000 nodes and 3.6 million links, while reducing solving time by up to 84% and training time by up to 79.6% compared to existing methods.

By Fangtong Zhou, Xiaorui Liu, Ruozhou Yu, Guoliang Xue
benchmarks
More like this →