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

2026-03-19

AI Summary

This work proposes BeamAgent, a framework that leverages a large language model (LLM) solely as a semantic parser to translate natural language instructions into structured spatial constraints under conditions of scarce domain-specific training data. By employing scene-aware prompting and a two-tier intent classification mechanism, the approach robustly generates constraints without requiring LLM fine-tuning. Subsequently, an alternating optimization algorithm jointly solves the discrete base station placement and continuous precoding problems, incorporating a penalty function method to balance bright-zone gain and dark-zone suppression. Evaluated in a ray-traced urban MIMO scenario, the method achieves a bright-zone power of 84.0 dB—7.1 dB higher than exhaustive zero-forcing and only 3.3 dB below the expert upper bound—while completing full-system optimization in under two seconds.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Search and Optimization: Mixed Discrete/Continuous Search
• Constraint Satisfaction and Optimization: Constraint Optimization

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

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.

Problem

• MIMO beamforming
• large language models
• joint site selection and precoding
• spatial constraints
• wireless communication optimization

Innovation

• LLM-aided beamforming
• decoupled intent parsing
• alternating optimization
• joint site selection and precoding
• spatial constraint translation