Skip to content
#artificial intelligence Conference Open access

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

Aug 2026 · 2026 IEEE/CIC International Conference on Communications in China (ICCC) · pp. 1449-1454 · 0 citations · 16 references
Computer Science

TL;DR

STR-Agent is proposed, an LLM-driven framework for QoS-aware routing in LEO satellite networks that significantly outperforms conventional baselines, and results demonstrate the potential of LLM-driven agent architectures to enable serviceaware and adaptive QoS routing in future LEO satellite networks.

Abstract

LEO satellite networks feature dynamic topologies, time-varying links, and diverse service requirements, which make conventional routing schemes difficult to support fine-grained quality-of-service (QoS) provisioning. Existing studies mainly optimize routing over network states with predefined objectives, but rarely address the practical challenge of translating unstructured natural-language service requests into adaptive routing decisions. To bridge this gap, we propose STR-Agent, an LLM-driven framework for QoS-aware routing in LEO satellite networks. The key innovation of STR-Agent lies in unifying intent perception, tool-based execution, experience accumulation, and reflection-based policy adaptation within a single agent architecture. Specifically, the Perception Module converts naturallanguage requests into structured routing semantics, while the Reflection Module dynamically adjusts the service-to-routingpolicy mapping according to real-time congestion conditions and historical routing outcomes, rather than relying on a fixed routing objective. In addition, we develop a specialized perception model, and construct a domain-specific supervised fine-tuning dataset for LEO service understanding. Simulation results in a Walker-Delta constellation show that STR-Agent significantly outperforms conventional baselines: it reduces end-to-end delay by up to 60% compared with DQ-Dijkstra, improves average intent-understanding accuracy from 45.4% to 92.45% after supervised fine-tuning, and the Reflection Module further reduces the delay by 120 ms at $\mathbf{6 0 0}$ Mbps. These results demonstrate the potential of LLM-driven agent architectures to enable serviceaware and adaptive QoS routing in future LEO satellite networks.

Read PDF

Similar papers

Review 2026

The Systems Architecture of LLM Multi-Agent Systems: Routing, Memory, and Resource Optimisation

This survey presents a systematic taxonomy and technical review of dynamic orchestration strategies designed to address communication overhead, KV cache management challenges, and increased token consumption within large Language Model-based Multi-Agent Systems.

Heet Nagoriya, H. Raithatha · 0 citations
2026

Aligning Routing With Service Intent in Logical Networks: A QoS-Driven Graph Attention Reinforcement Learning Framework

Network virtualization enables the creation of multiple logical networks on shared physical infrastructure, each supporting homogeneous traffic with a dedicated Quality of Service (QoS) objective. This shifts the routing problem from arbitrating among heterogeneous flows to holistically orchestrating traffic toward a s...

Xiao-Long Cui, Xue-Bin Tang, Yu-Chen Wang et al. · 0 citations
Book Open access Aug 2026

G-STAR: Graph-based Scheduling with Trace-driven Adaptive Routing for Industrial LLM-based Multi-Agent Systems

G-STAR is a general graph-based scheduling framework that formalizes complex MAS pipelines as attributed Directed Acyclic Graphs (DAGs) and develops an industry-grade orchestration stack with asynchronous execution, resilient serving, and audit-friendly artifacts, offering a practical solution for optimizing web-scale...

Jia-Bao Song, Yun-Sheng Xia, Bei-Bei Kong et al. · 0 citations
Conference Aug 2026

Global Load-Aware Routing Algorithm for Multi-Service LEO Networks: A Graph-Based DRL Approach

To address the challenges of multi-service congestion and load imbalance in Low Earth Orbit (LEO) networks, stemming from highly dynamic spatio-temporal characteristics and constrained link capacities, this paper proposes a joint optimization method for routing and load balancing based on Graph Neural Networks (GNN) an...

Jing-Chao Wang, Yi-Chuan Guo, Liang Wang et al. · 0 citations
Open access 2026

5G-Aware Incremental Routing and Scheduling for Dynamic Time-Triggered Flow Admission in Time-Sensitive Networks

: Mobile edge services require deterministic communication across Time-Sensitive Networking (TSN) and 5G access, where the standardized integration architecture exposes the 5G System (5GS) to the TSN controller as a logical bridge. We study dynamic admission of time-triggered (TT) flows using reported 5GS bridge delay...

Zhi-Hao Liu, Yi Zhang, Wei Zhang et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.