mlsanityData to 14 Oct 2026

Asynchronous Risk-Aware Multi-Agent Packet Routing for Ultra-Dense LEO Satellite Networks

arXiv 2510.27506 ↗First posted 31 Oct 2025cs.NI cs.IT cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The rise of ultra-dense LEO constellations creates a complex and asynchronous network environment, driven by their massive scale, dynamic topologies, and significant delays. This unique complexity demands an adaptive packet routing algorithm that is asynchronous, risk-aware, and capable of balancing diverse and often conflicting QoS objectives in a decentralized manner. However, existing methods fail to address this need, as they typically rely on impractical synchronous decision-making and/or risk-oblivious approaches. To tackle this gap, we introduce PRIMAL, an event-driven multi-agent routing framework designed specifically to allow each satellite to act independently on its own event-driven timeline, while managing the risk of worst-case performance degradation via a principled primal-dual approach. This is achieved by enabling agents to learn the full cost distribution of the targeted QoS objectives and constrain tail-end risks. Extensive simulations on a LEO constellation with 1584 satellites validate its superiority in effectively optimizing latency and balancing load. Compared to a recent risk-oblivious baseline, it reduces queuing delay by over 70%, and achieves a nearly 12 ms end-to-end delay reduction in loaded scenarios. This is accomplished by resolving the core conflict between naive shortest-path finding and congestion avoidance, highlighting such autonomous risk-awareness as a key to robust routing.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 40 references that are in the map. First posted on arXiv 31 Oct 2025.

Builds on

15 of 40 references.

References · 15

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2018Implicit Quantile Networks for Distributional Reinforcement Learningcited by 369
  3. 2019Constrained Reinforcement Learning Has Zero Duality Gapcited by 151
  4. 2020Satellite Communications in the New Space Era: A Survey and Future Challengescited by 36
  5. 2024Generative AI Agents with Large Language Model for Satellite Networks via a Mixture of Experts Transmissioncited by 35
  6. 2024Interactive AI with Retrieval-Augmented Generation for Next Generation Networkingcited by 34
  7. 2017Deep Reinforcement Learning for Event-Driven Multi-Agent Decision Processescited by 21
  8. 2022Asynchronous Actor-Critic for Multi-Agent Reinforcement Learningcited by 18
  9. 2023Asynchronous Multi-Agent Reinforcement Learning for Efficient Real-Time Multi-Robot Cooperative Explorationcited by 18
  10. 2022Revisiting Discrete Soft Actor-Criticcited by 13
  11. 2021A Survey on Non-Geostationary Satellite Systems: The Communication Perspectivecited by 12
  12. 2022Quantile Constrained Reinforcement Learning: A Reinforcement Learning Framework Constraining Outage Probabilitycited by 9
3 more
  1. 2023Dynamic Routing for Integrated Satellite-Terrestrial Networks: A Constrained Multi-Agent Reinforcement Learning Approachcited by 9
  2. 2020Integrating LEO Satellites and Multi-UAV Reinforcement Learning for Hybrid FSO/RF Non-Terrestrial Networkscited by 7
  3. 2024Continual Deep Reinforcement Learning for Decentralized Satellite Routingcited by 6

Built on by

Not cited yet.