From Heuristic Selection to Automated Algorithm Design: LLMs Benefit from Strong Priors

TL;DR

This paper shows that providing high-quality algorithm examples and leveraging prior benchmarks significantly improves LLM-driven automated algorithm design, leading to better performance on black-box optimization tasks.

Contribution

It introduces a method to incorporate prior benchmark algorithms into LLM-based optimization, enhancing effectiveness and robustness.

Findings

High-quality prompt examples improve LLM optimization performance.

Leveraging prior benchmarks outperforms adaptive prompt strategies.

Superior results achieved on pbo and bbob benchmarks.

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.