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

arXiv: https://arxiv.org/abs/2603.18855 · HTML: https://mlsanity.com/paper/2603.18855/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 41 references that are in the map.
- First posted on arXiv 19 Mar 2026.

## Builds on (most cited first, 25 of 25)

- [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023)
- [RadioUNet: Fast Radio Map Estimation with Convolutional Neural Networks](https://mlsanity.com/paper/1911.09002/) (2019)
- [Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles, Key Techniques, and Opportunities](https://mlsanity.com/paper/2405.10825/) (2024)
- [NetLLM: Adapting Large Language Models for Networking](https://mlsanity.com/paper/2402.02338/) (2024)
- [Sionna RT: Differentiable Ray Tracing for Radio Propagation Modeling](https://mlsanity.com/paper/2303.11103/) (2023)
- [A Tutorial on Environment-Aware Communications via Channel Knowledge Map for 6G](https://mlsanity.com/paper/2309.07460/) (2023)
- [RadioDiff: An Effective Generative Diffusion Model for Sampling-Free Dynamic Radio Map Construction](https://mlsanity.com/paper/2408.08593/) (2024)
- [Large Language Model Enhanced Multi-Agent Systems for 6G Communications](https://mlsanity.com/paper/2312.07850/) (2023)
- [Intelligent Reflecting Surface Enhanced Wireless Network via Joint Active and Passive Beamforming](https://mlsanity.com/paper/1810.03961/) (2018)
- [When Large Language Model Agents Meet 6G Networks: Perception, Grounding, and Alignment](https://mlsanity.com/paper/2401.07764/) (2024)
- [TelecomGPT: A Framework to Build Telecom-Specfic Large Language Models](https://mlsanity.com/paper/2407.09424/) (2024)
- [WirelessGPT: A Generative Pre-trained Multi-task Learning Framework for Wireless Communication](https://mlsanity.com/paper/2502.06877/) (2025)
- [WirelessAgent: Large Language Model Agents for Intelligent Wireless Networks](https://mlsanity.com/paper/2505.01074/) (2025)
- [Large Language Model (LLM)-enabled In-context Learning for Wireless Network Optimization: A Case Study of Power Control](https://mlsanity.com/paper/2408.00214/) (2024)
- [RadioDiff-k2: Helmholtz Equation Informed Generative Diffusion Model for Multi-Path Aware Radio Map Construction](https://mlsanity.com/paper/2504.15623/) (2025)
- [Toward Immersive Communications in 6G](https://mlsanity.com/paper/2303.05283/) (2023)
- [RadioDiff-3D: A 3D×3D Radio Map Dataset and Generative Diffusion Based Benchmark for 6G Environment-Aware Communication](https://mlsanity.com/paper/2507.12166/) (2025)
- [Adaptive Resource Allocation Optimization Using Large Language Models in Dynamic Wireless Environments](https://mlsanity.com/paper/2502.02287/) (2025)
- [ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks](https://mlsanity.com/paper/2601.19607/) (2026)
- [WirelessAgent++: Automated Agentic Workflow Design and Benchmarking for Wireless Networks](https://mlsanity.com/paper/2603.00501/) (2026)
- [LLM4MG: Adapting Large Language Model for Multipath Generation via Synesthesia of Machines](https://mlsanity.com/paper/2509.14711/) (2025)
- [Bridging 6G IoT and AI: LLM-Based Efficient Approach for Physical Layer's Optimization Tasks](https://mlsanity.com/paper/2602.06819/) (2026)
- [Wireless Power Control Based on Large Language Models](https://mlsanity.com/paper/2603.00474/) (2026)
- [TelePlanNet: An AI-Driven Framework for Efficient Telecom Network Planning](https://mlsanity.com/paper/2505.13831/) (2025)
- [Base Station Deployment under EMF constrain by Deep Reinforcement learning](https://mlsanity.com/paper/2601.02385/) (2025)

## Built on by (most cited first, 1 of 1)

- [AgenticPrecoding: LLM-Empowered Multi-Agent System for Precoding Optimization](https://mlsanity.com/paper/2605.06443/) (2026)

## Abstract (arXiv)

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.