LLM-Enabled Automated Algorithm Design for Multiuser Fluid Antenna Communications

2026-05-14

AI Summary

This work addresses the combinatorial challenge of jointly optimizing large-scale port selection and beamforming in fluid antenna systems by proposing a novel automatic algorithm design framework based on large language models (LLMs). The framework operates without human intervention, either enhancing the crossover and mutation operators of genetic algorithms or generating entirely new heuristic strategies—termed AutoPort—from scratch to maximize SINR performance under user fairness constraints. As the first study to leverage LLMs for automatically synthesizing hyper-heuristic algorithms in fluid antenna systems, the proposed approach demonstrates strong empirical performance, closely approximating the optimal solution in simulations and significantly outperforming conventional genetic algorithms as well as existing deep learning-based methods.

Abstract

Fluid antenna is a new reconfigurable antenna technology that can dynamically adjust the positions or ports of radiating elements and therefore provides a new degree of freedom for wireless communications. However, the associated port selection is a challenging large-scale combinatorial optimization problem and difficult to solve. Existing manually designed heuristic algorithms are not only labor-intensive, but cannot achieve satisfactory performance. In this paper, we propose a novel paradigm that leverages large language models (LLMs) for automated design of optimization algorithms for fluid antenna systems without manual hyperheuristic tuning. Specifically, we study the problem of maximizing the minimum signal-to-interference-plus-noise ratio (SINR) in the downlink to ensure fairness among users by optimizing port selection and beamforming. We investigate two LLM-enabled algorithm optimization strategies. The first is to optimize the crossover and mutation operations to enhance the performance of the well-known genetic algorithm and the second is to design AutoPort, a new heuristic from scratch by LLM, to solve the optimization problem. Simulation results verify that the proposed method can achieve near-optimal performance and significant improvement over the conventional genetic algorithm and the deep learning approach.

Problem

• fluid antenna
• port selection
• combinatorial optimization
• SINR maximization
• multiuser fairness

Innovation

• Large Language Models
• Fluid Antenna Systems
• Automated Algorithm Design
• Combinatorial Optimization
• AutoPort