Automated Algorithm Design with LLMs: A Benchmark-Assisted Approach to Black-Box Optimization

Qi Huang, Furong Ye, Thomas Bäck, Niki van Stein

Keywords: LLM-driven Optimization; Black-box Optimization; Benchmark

TL;DR: We propose a benchmark-assisted approach of LLM-driven Black-Box Optimization, motivated by our findings that the given example code in prompts obtain the most significant impact on code generation of LLM-driven approaches.

Abstract:

Large Language Models (LLMs) have already been widely adopted for automated algorithm design, demonstrating strong abilities in generating and evolving algorithms across various fields.
Existing work has largely focused on examining their effectiveness in solving specific problems, with search strategies primarily guided by adaptive prompt designs.
In this paper, through investigating the token-wise attribution of the prompts to LLM-generated algorithmic codes, we show that providing high-quality algorithmic code examples can substantially improve the performance of the LLM-driven optimization.
Building upon this insight, we propose leveraging prior benchmark algorithms to guide LLM-driven optimization and demonstrate superior performance on two black-box optimization benchmarks: the pseudo-Boolean optimization suite (pbo) and the black-box optimization suite (bbob).
Our findings highlight the value of integrating benchmarking studies to enhance both efficiency and robustness of the LLM-driven black-box optimization methods. The source code and auxiliary materials are provided at https://anonymous.4open.science/r/ICLR2026-submissionID2452-D709 .

Primary Area: optimization

Submission Number: 2452