LLM-Empowered Agentic MAC Protocols: A Dynamic Stackelberg Game Approach

2025-10-12

AI Summary

To address the poor generalizability, weak robustness, and reliance on retraining inherent in conventional wireless MAC protocols, this paper proposes the first large language model (LLM)-based multi-agent MAC protocol framework. Methodologically, it innovatively models uplink and downlink transmissions as a dynamic multi-follower Stackelberg game, integrates an LLM-driven agent coordination mechanism, and employs Protocol Action Grammar (PAG) to ensure syntactic and semantic reliability of generated protocols. Crucially, the framework enables semantic-level adaptive protocol generation without retraining and maintains equilibrium convergence under dynamic user population changes. Simulation results demonstrate that, compared to traditional baselines, the proposed framework achieves a 77.6% increase in system throughput and a 65.2% improvement in fairness, while significantly enhancing both generalizability and robustness across diverse network conditions.

Technology Category

• Multiagent Systems: Agent Communication
• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Medium Access Control (MAC) protocols, essential for wireless networks, are typically manually configured. While deep reinforcement learning (DRL)-based protocols enhance task-specified network performance, they suffer from poor generalizability and resilience, demanding costly retraining to adapt to dynamic environments. To overcome this limitation, we introduce a game-theoretic LLM-empowered multi-agent DRL (MARL) framework, in which the uplink transmission between a base station and a varying number of user equipments is modeled as a dynamic multi-follower Stackelberg game (MFSG), capturing the network's natural hierarchical structure. Within this game, LLM-driven agents, coordinated through proximal policy optimization (PPO), synthesize adaptive, semantic MAC protocols in response to network dynamics. Protocol action grammar (PAG) is employed to ensure the reliability and efficiency of this process. Under this system, we further analyze the existence and convergence behavior in terms of a Stackelberg equilibrium by studying the learning dynamics of LLM-empowered unified policies in response to changing followers. Simulations corroborate that our framework achieves a 77.6% greater throughput and a 65.2% fairness improvement over conventional baselines. Besides, our framework generalizes excellently to a fluctuating number of users without requiring retraining or architectural changes.

Problem

• Developing adaptive MAC protocols using LLM-empowered multi-agent reinforcement learning
• Overcoming poor generalizability of conventional DRL protocols in dynamic wireless networks
• Modeling uplink transmissions as dynamic Stackelberg games for hierarchical network optimization

Innovation

• LLM-empowered multi-agent DRL framework for MAC protocols
• Dynamic Stackelberg game models hierarchical network structure
• Protocol action grammar ensures reliable semantic protocol synthesis