Prompt-Tuned LLM-Augmented DRL for Dynamic O-RAN Network Slicing

TL;DR

This paper introduces a novel prompt-tuned LLM-augmented deep reinforcement learning framework for dynamic O-RAN network slicing, improving decision-making, convergence speed, and adaptability in complex wireless environments.

Contribution

It proposes a prompt-based adaptation method that enhances DRL in O-RAN slicing by integrating learnable prompts with an LLM, avoiding full model fine-tuning.

Findings

Accelerates convergence of RL agents

Outperforms baseline methods in reward optimization

Enables scalable and adaptive resource management

Abstract

Modern wireless networks must adapt to dynamic conditions while efficiently managing diverse service demands. Traditional deep reinforcement learning (DRL) struggles in these environments, as scattered and evolving feedback makes optimal decision-making challenging. Large Language Models (LLMs) offer a solution by structuring unorganized network feedback into meaningful latent representations, helping RL agents recognize patterns more effectively. For example, in O-RAN slicing, concepts like SNR, power levels and throughput are semantically related, and LLMs can naturally cluster them, providing a more interpretable state representation. To leverage this capability, we introduce a contextualization-based adaptation method that integrates learnable prompts into an LLM-augmented DRL framework. Instead of relying on full model fine-tuning, we refine state representations through task-specific prompts that dynamically adjust to network conditions. Utilizing ORANSight, an LLM trained on O-RAN knowledge, we develop Prompt-Augmented Multi agent RL (PA-MRL) framework. Learnable prompts optimize both semantic clustering and RL objectives, allowing RL agents to achieve higher rewards in fewer iterations and adapt more efficiently. By incorporating prompt-augmented learning, our approach enables faster, more scalable, and adaptive resource allocation in O-RAN slicing. Experimental results show that it accelerates convergence and outperforms other baselines.