LLM4MAC: An LLM-Driven Reinforcement Learning Framework for MAC Protocol Emergence

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Tan, Renxuan, Li, Rongpeng, Zhao, Zhifeng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916649534226432
author Tan, Renxuan
Li, Rongpeng
Zhao, Zhifeng
author_facet Tan, Renxuan
Li, Rongpeng
Zhao, Zhifeng
contents With the advent of 6G systems, emerging hyper-connected ecosystems necessitate agile and adaptive medium access control (MAC) protocols to contend with network dynamics and diverse service requirements. We propose LLM4MAC, a novel framework that harnesses large language models (LLMs) within a reinforcement learning paradigm to drive MAC protocol emergence. By reformulating uplink data transmission scheduling as a semantics-generalized partially observable Markov game (POMG), LLM4MAC encodes network operations in natural language, while proximal policy optimization (PPO) ensures continuous alignment with the evolving network dynamics. A structured identity embedding (SIE) mechanism further enables robust coordination among heterogeneous agents. Extensive simulations demonstrate that on top of a compact LLM, which is purposefully selected to balance performance with resource efficiency, the protocol emerging from LLM4MAC outperforms comparative baselines in throughput and generalization.
format Preprint
id arxiv_https___arxiv_org_abs_2503_08123
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM4MAC: An LLM-Driven Reinforcement Learning Framework for MAC Protocol Emergence
Tan, Renxuan
Li, Rongpeng
Zhao, Zhifeng
Networking and Internet Architecture
With the advent of 6G systems, emerging hyper-connected ecosystems necessitate agile and adaptive medium access control (MAC) protocols to contend with network dynamics and diverse service requirements. We propose LLM4MAC, a novel framework that harnesses large language models (LLMs) within a reinforcement learning paradigm to drive MAC protocol emergence. By reformulating uplink data transmission scheduling as a semantics-generalized partially observable Markov game (POMG), LLM4MAC encodes network operations in natural language, while proximal policy optimization (PPO) ensures continuous alignment with the evolving network dynamics. A structured identity embedding (SIE) mechanism further enables robust coordination among heterogeneous agents. Extensive simulations demonstrate that on top of a compact LLM, which is purposefully selected to balance performance with resource efficiency, the protocol emerging from LLM4MAC outperforms comparative baselines in throughput and generalization.
title LLM4MAC: An LLM-Driven Reinforcement Learning Framework for MAC Protocol Emergence
topic Networking and Internet Architecture
url https://arxiv.org/abs/2503.08123