English

LLM-OptiRA: LLM-Driven Optimization of Resource Allocation for Non-Convex Problems in Wireless Communications

Computation and Language 2025-09-29 v2 Machine Learning

Abstract

Solving non-convex resource allocation problems poses significant challenges in wireless communication systems, often beyond the capability of traditional optimization techniques. To address this issue, we propose LLM-OptiRA, the first framework that leverages large language models (LLMs) to automatically detect and transform non-convex components into solvable forms, enabling fully automated resolution of non-convex resource allocation problems in wireless communication systems. LLM-OptiRA not only simplifies problem-solving by reducing reliance on expert knowledge, but also integrates error correction and feasibility validation mechanisms to ensure robustness. Experimental results show that LLM-OptiRA achieves an execution rate of 96% and a success rate of 80% on GPT-4, significantly outperforming baseline approaches in complex optimization tasks across diverse scenarios.

Keywords

Cite

@article{arxiv.2505.02091,
  title  = {LLM-OptiRA: LLM-Driven Optimization of Resource Allocation for Non-Convex Problems in Wireless Communications},
  author = {Xinyue Peng and Yanming Liu and Yihan Cang and Chaoqun Cao and Ming Chen},
  journal= {arXiv preprint arXiv:2505.02091},
  year   = {2025}
}

Comments

6 pages,4 figures

R2 v1 2026-06-28T23:20:36.297Z