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

arXiv: https://arxiv.org/abs/2506.00574 · HTML: https://mlsanity.com/paper/2506.00574/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 31 May 2025.

## Builds on (most cited first, 16 of 16)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021)
- [The Power of Scale for Parameter-Efficient Prompt Tuning](https://mlsanity.com/paper/2104.08691/) (2021)
- [Understanding O-RAN: Architecture, Interfaces, Algorithms, Security, and Research Challenges](https://mlsanity.com/paper/2202.01032/) (2022)
- [Large Generative AI Models for Telecom: The Next Big Thing?](https://mlsanity.com/paper/2306.10249/) (2023)
- [Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learning](https://mlsanity.com/paper/2002.06215/) (2020)
- [Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach](https://mlsanity.com/paper/2311.13884/) (2023)
- [Understanding Telecom Language Through Large Language Models](https://mlsanity.com/paper/2306.07933/) (2023)
- [LLM-Empowered State Representation for Reinforcement Learning](https://mlsanity.com/paper/2407.13237/) (2024)
- [ORAN-Bench-13K: An Open Source Benchmark for Assessing LLMs in Open Radio Access Networks](https://mlsanity.com/paper/2407.06245/) (2024)
- [LLM-Based Intent Processing and Network Optimization Using Attention-Based Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2406.06059/) (2024)
- [ORANSight-2.0: Foundational LLMs for O-RAN](https://mlsanity.com/paper/2503.05200/) (2025)
- [Meta Reinforcement Learning Approach for Adaptive Resource Optimization in O-RAN](https://mlsanity.com/paper/2410.03737/) (2024)
- [Communication and Control Co-Design in 6G: Sequential Decision-Making with LLMs](https://mlsanity.com/paper/2407.06227/) (2024)

## Built on by (most cited first, 2 of 2)

- [AgentRAN: An Agentic AI Architecture for Autonomous Control of Open 6G Networks](https://mlsanity.com/paper/2508.17778/) (2025)
- [Task Specific Sharpness Aware O-RAN Resource Management using Multi Agent Reinforcement Learning](https://mlsanity.com/paper/2511.15002/) (2025)

## Abstract (arXiv)

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.