In near-field extremely large-scale multiple-input multiple-output (XL-MIMO) systems, spherical wavefront propagation expands the traditional beam codebook into the joint angular-distance domain, rendering conventional beam training prohibitively inefficient, especially in complex 3-dimensional (3D) low-altitude environments. Furthermore, since near-field beam variations are deeply coupled not only with user positions but also with the physical surroundings, precise beam alignment demands profound environmental understanding capabilities. To address this, we propose a large language model (LLM)-driven multimodal framework that fuses historical GPS data, RGB image, LiDAR data, and strategically designed task-specific textual prompts. By utilizing the powerful emergent reasoning and generalization capabilities of the LLM, our approach learns complex spatial dynamics to achieve superior environmental comprehension...
@article{arxiv.2603.16143,
title = {Structure-Aware Multimodal LLM Framework for Trustworthy Near-Field Beam Prediction},
author = {Mengyuan Li and Qianfan Lu and Jiachen Tian and Hongjun Hu and Yu Han and Xiao Li and Chao-kai Wen and Shi Jin},
journal= {arXiv preprint arXiv:2603.16143},
year = {2026}
}