BeamAgent: LLM-Aided MIMO Beamforming with Decoupled Intent Parsing and Alternating Optimization for Joint Site Selection and Precoding

TL;DR

BeamAgent introduces a novel LLM-assisted MIMO beamforming framework that decouples semantic intent parsing from numerical optimization, enabling efficient joint site selection and precoding with minimal fine-tuning.

Contribution

The paper presents BeamAgent, a framework that uses LLMs for semantic parsing and a dedicated optimizer for physical-layer optimization, improving efficiency and robustness in wireless MIMO beamforming.

Findings

Achieves 84.0 dB bright-zone power, outperforming zero-forcing by 7.1 dB.

Reaches within 3.3 dB of expert upper bound.

Completes optimization in under 2 seconds on a laptop.

Abstract

Integrating large language models (LLMs) into wireless communication optimization is a promising yet challenging direction. Existing approaches either use LLMs as black-box solvers or code generators, tightly coupling them with numerical computation. However, LLMs lack the precision required for physical-layer optimization, and the scarcity of wireless training data makes domain-specific fine-tuning impractical. We propose BeamAgent, an LLM-aided MIMO beamforming framework that explicitly decouples semantic intent parsing from numerical optimization. The LLM serves solely as a semantic translator that converts natural language descriptions into structured spatial constraints. A dedicated gradient-based optimizer then jointly solves the discrete base station site selection and continuous precoding design through an alternating optimization algorithm. A scene-aware prompt enables grounded spatial reasoning without fine-tuning, and a multi-round interaction mechanism with dual-layer intent classification ensures robust constraint verification. A penalty-based loss function enforces dark-zone power constraints while releasing optimization degrees of freedom for bright-zone gain maximization. Experiments on a ray-tracing-based urban MIMO scenario show that BeamAgent achieves a bright-zone power of 84.0\,dB, outperforming exhaustive zero-forcing by 7.1 dB under the same dark-zone constraint. The end-to-end system reaches within 3.3 dB of the expert upper bound, with the full optimization completing in under 2 s on a laptop.