Saved in:
Bibliographic Details
Main Authors: Huang, Yunsong, Wang, Hui-Ming, Yan, Qingli, Wang, Zhaowei
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2508.12728
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915449103450112
author Huang, Yunsong
Wang, Hui-Ming
Yan, Qingli
Wang, Zhaowei
author_facet Huang, Yunsong
Wang, Hui-Ming
Yan, Qingli
Wang, Zhaowei
contents The evolution of 6G networks demands ultra-massive connectivity and intelligent radio environments, yet existing reconfigurable intelligent surface (RIS) technologies face critical limitations in hardware efficiency, dynamic control, and scalability. This paper introduces LLM-RIMSA, a transformative framework that integrates large language models (LLMs) with a novel reconfigurable intelligent metasurface antenna (RIMSA) architecture to address these challenges. Unlike conventional RIS designs, RIMSA employs parallel coaxial feeding and 2D metasurface integration, enabling each individual metamaterial element to independently adjust both its amplitude and phase. While traditional optimization and deep learning (DL) methods struggle with high-dimensional state spaces and prohibitive training costs for RIMSA control, LLM-RIMSA leverages pre-trained LLMs cross-modal reasoning and few-shot learning capabilities to dynamically optimize RIMSA configurations. Simulations demonstrate that LLM-RIMSA achieves state-of-the-art performance, outperforming conventional DL-based methods in sum rate while reducing training overhead. The proposed framework pave the way for LLM-driven intelligent radio environments.
format Preprint
id arxiv_https___arxiv_org_abs_2508_12728
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LLM-RIMSA: Large Language Models driven Reconfigurable Intelligent Metasurface Antenna Systems
Huang, Yunsong
Wang, Hui-Ming
Yan, Qingli
Wang, Zhaowei
Signal Processing
The evolution of 6G networks demands ultra-massive connectivity and intelligent radio environments, yet existing reconfigurable intelligent surface (RIS) technologies face critical limitations in hardware efficiency, dynamic control, and scalability. This paper introduces LLM-RIMSA, a transformative framework that integrates large language models (LLMs) with a novel reconfigurable intelligent metasurface antenna (RIMSA) architecture to address these challenges. Unlike conventional RIS designs, RIMSA employs parallel coaxial feeding and 2D metasurface integration, enabling each individual metamaterial element to independently adjust both its amplitude and phase. While traditional optimization and deep learning (DL) methods struggle with high-dimensional state spaces and prohibitive training costs for RIMSA control, LLM-RIMSA leverages pre-trained LLMs cross-modal reasoning and few-shot learning capabilities to dynamically optimize RIMSA configurations. Simulations demonstrate that LLM-RIMSA achieves state-of-the-art performance, outperforming conventional DL-based methods in sum rate while reducing training overhead. The proposed framework pave the way for LLM-driven intelligent radio environments.
title LLM-RIMSA: Large Language Models driven Reconfigurable Intelligent Metasurface Antenna Systems
topic Signal Processing
url https://arxiv.org/abs/2508.12728