Beyond LLM-GA: Secure Fluid Antenna Systems with ReEvo-Designed Memetic Algorithm
Abstract
Fluid antenna systems (FASs) offer significant spatial flexibility, yet securing them against eavesdropping is critical for practical FAS deployment in military, satellite, and internet-of-things networks. Although large language model (LLM)-assisted genetic algorithms (LLM-GAs) can address this secure FAS port selection problem, whether further algorithmic improvement is possible warrants deeper investigation. To this end, we propose a memetic algorithm based on reflective evolution (ReEvo). Unlike the state-of-the-art LLM-GAs, which design only crossover or mutation operators with an LLM, our algorithm leverages an LLM to evolve dedicated crossover, mutation, and local-search operators offline. These operators are then embedded into a memetic search framework, thereby obviating any online LLM queries during execution. Simulation results at equal generation counts demonstrate that our proposed algorithm achieves a higher secure sum-rate than the conventional GA and the state-of-the-art LLM-GAs.
Related
- Impact of Antenna Position Errors on TDMA and NOMA in Pinching-Antenna Systems
- S-PASS: Star-Topology Pinching-Antenna Systems with Pipelined Antenna Pre-Positioning
- Learning Representative Port Subsets for Efficient Fluid Antenna Systems
- Secrecy Sum-Rate Maximization for RSMA-Enabled Pinching-Antenna Systems
- Design and Analysis of Pinching-Antenna Systems With Radially Deployed Waveguides (X-PASS)
BibTeX
@misc{xu2026beyond,
title = {{Beyond LLM-GA: Secure Fluid Antenna Systems with ReEvo-Designed Memetic Algorithm}},
author = {Hanyong Xu and Zhaolai Dang and Tong Zhang},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.10235},
eprint = {2610.10235},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.10235},
}
RIS
TY - UNPB
TI - Beyond LLM-GA: Secure Fluid Antenna Systems with ReEvo-Designed Memetic Algorithm
AU - Hanyong Xu
AU - Zhaolai Dang
AU - Tong Zhang
PY - 2026
DA - 2026/10/26
PB - arXiv
DO - 10.48550/arxiv.2610.10235
UR - https://arxiv.org/abs/2610.10235
AB - Fluid antenna systems (FASs) offer significant spatial flexibility, yet securing them against eavesdropping is critical for practical FAS deployment in military, satellite, and internet-of-things networks. Although large language model (LLM)-assisted genetic algorithms (LLM-GAs) can address this secure FAS port selection problem, whether further algorithmic improvement is possible warrants deeper investigation. To this end, we propose a memetic algorithm based on reflective evolution (ReEvo). Unlike the state-of-the-art LLM-GAs, which design only crossover or mutation operators with an LLM, our algorithm leverages an LLM to evolve dedicated crossover, mutation, and local-search operators offline. These operators are then embedded into a memetic search framework, thereby obviating any online LLM queries during execution. Simulation results at equal generation counts demonstrate that our proposed algorithm achieves a higher secure sum-rate than the conventional GA and the state-of-the-art LLM-GAs.
ER -