Skip to main content
Search

Hanyong Xu

1 related articles

Subscribe to updates
  1. arXiv

    ReEvo evolves crossover, mutation, and local-search operators offline for a memetic algorithm that secures fluid-antenna port selection, beating GA and two LLM-GA baselines in secure sum-rate

    For the mixed-integer nonconvex problem of joint secure port selection and beamforming in multiuser downlink fluid antenna systems, the authors propose a reflective-evolution (ReEvo) memetic algorithm in which a large language model evolves three complementary discrete operators offline—crossover, mutation, and local search—under a secrecy-driven fitness computed via secure WMMSE beamforming, with the frozen operators requiring no online LLM queries; at equal generation counts it achieves higher secure sum-rate than a conventional GA and two LLM-GA baselines that design only a single operator.

You’re all caught up