Resilient LLM-Empowered Semantic MAC Protocols via Zero-Shot Adaptation and Knowledge Distillation

2025/05/22 by Yong-Jun Kim, Jihong Park, Kim, Yongjun +5 · 2 citations
Computer Science · Engineering · #FOS: Computer and information sciences #IoT Networks and Protocols #Networking and Internet Architecture (cs.NI) #Software-Defined Networks and 5G #Wireless Networks and Protocols

paper · pdf · doi:10.48550/arxiv.2505.21518

openalex publication_date 2025/05/22 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Neural network-based medium access control (MAC) protocol models (NPMs) improve goodput through site-specific operations but are vulnerable to shifts from their training network environments, such as changes in the number of user equipments (UEs) severely degrade goodput. To enhance resilience against such environmental shifts, we propose three novel semantic MAC protocol frameworks empowered by large language models (LLMs). First, we introduce a token-based protocol model (TPM), where an LLM generates MAC signaling messages. By editing LLM instruction prompts, TPM enables instant adaptation, which can be further enhanced by TextGrad, an LLM-based automated prompt optimizer. TPM inference is fast but coarse due to the lack of real interactions with the changed environment, and computationally intensive due to the large size of the LLM. To improve goodput and computation efficiency, we develop T2NPM, which transfers and augments TPM knowledge into an NPM via knowledge distillation (KD). Integrating TPM and T2NPM, we propose T3NPM, which employs TPM in the early phase and switches to T2NPM later. To optimize this phase switching, we design a novel metric of meta-resilience, which quantifies resilience to unknown target goodput after environmental shifts. Simulations corroborate that T3NPM achieves 20.56% higher meta-resilience than NPM with 19.8x lower computation cost than TPM in FLOPS.

Citations

• LLM4MAC: An LLM-Driven Reinforcement Learning Framework for MAC Protocol Emergence
• Port-LLM: A Port Prediction Method for Fluid Antenna based on Large Language Models
• Towards Secure Intelligent O-RAN Architecture: Vulnerabilities, Threats and Promising Technical Solutions using LLMs
• Beam Prediction based on Large Language Models
• TextGrad: Automatic "Differentiation" via Text
• A deep-learning-based MAC for integrating channel access, rate adaptation and channel switch
• Towards Hierarchical Multi-Agent Workflows for Zero-Shot Prompt Optimization
• SOLAR 10.7B: Scaling Large Language Models with Simple yet Effective Depth Up-Scaling
• Large AI Model Empowered Multimodal Semantic Communications
• Large AI Model Empowered Multimodal Semantic Communications
• Understanding Telecom Language Through Large Language Models
• Evolution of MAC Protocols in the Machine Learning Decade: A Comprehensive Survey
• Towards Semantic Communication Protocols: A Probabilistic Logic Perspective
• Towards Understanding Knowledge Distillation
• Born Again Neural Networks
• Why Comparing Single Performance Scores Does Not Allow to Draw Conclusions About Machine Learning Approaches
• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• Multiagent Cooperation and Competition with Deep Reinforcement Learning
• Continuous control with deep reinforcement learning
• The Meta Distribution of the SIR in Poisson Bipolar and Cellular\n Networks
• Playing Atari with Deep Reinforcement Learning
• Prompt Engineering or Fine-Tuning: An Empirical Assessment of LLMs for Code
• Large Generative AI Models for Telecom: The Next Big Thing?

Cited by

• LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach
• Resilient-native and Intelligent NextG Systems

Related

• LLM4MAC: An LLM-Driven Reinforcement Learning Framework for MAC Protocol Emergence
• Towards Semantic Communication Protocols for 6G: From Protocol Learning to Language-Oriented Approaches
• Towards Semantic Communication Protocols: A Probabilistic Logic Perspective
• LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach
• Adapting Large Language Models for Improving TCP Fairness over WiFi