Large Artificial Intelligence Model Guided Deep Reinforcement Learning for Resource Allocation in Non Terrestrial Networks

2026-01-13

AI Summary

This work proposes a novel framework integrating large language models (LLMs) with deep reinforcement learning (DRL) to address the degraded resource allocation performance of non-terrestrial networks under adverse weather conditions and the limited generalization capability of conventional approaches. The method uniquely employs an LLM as a high-level coordinator that dynamically shapes the reward function of DRL agents through semantically informed guidance, enabling efficient and adaptive resource scheduling. Experimental results demonstrate that, compared to traditional DRL methods, the proposed approach achieves an average performance improvement of 40% in terms of throughput, fairness, and outage probability under normal weather conditions, with gains increasing to 64% under extreme weather. These results highlight a significant enhancement in both robustness and generalization of the learned policy.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information

Abstract

Large AI Model (LAM) have been proposed to applications of Non-Terrestrial Networks (NTN), that offer better performance with its great generalization and reduced task specific trainings. In this paper, we propose a Deep Reinforcement Learning (DRL) agent that is guided by a Large Language Model (LLM). The LLM operates as a high level coordinator that generates textual guidance that shape the reward of the DRL agent during training. The results show that the LAM-DRL outperforms the traditional DRL by 40% in nominal weather scenarios and 64% in extreme weather scenarios compared to heuristics in terms of throughput, fairness, and outage probability.

Problem

• Resource Allocation
• Non-Terrestrial Networks
• Throughput
• Fairness
• Outage Probability

Innovation

• Large Language Model
• Deep Reinforcement Learning
• Non-Terrestrial Networks
• Resource Allocation
• Reward Shaping