We propose a framework for automated discovery and composition of metaheuristic operators using large language models (LLMs). The method begins with generation of candidate algorithms, followed by LLM-guided selection of impactful operators, iterative construction of specialized operator variants, and final synthesis of an adaptive optimizer. The approach emphasizes task coverage rather than single-metric optimization, producing complementary operators specialized for different problem characteristics. These operators are subsequently integrated into an adaptive algorithm via LLM-driven parameter control and selection mechanisms. This work is submitted as a competition entry for LLM-generated metaheuristics evaluated on the GNBG benchmark.
Paweł Kolendo, Michal Pluháček· GECCO Companion· 0 citations
These findings suggest that direct configuration prediction provides a robust approach despite ambiguity in the parameter space, and are compared to a regression-based performance prediction model, a multiple-choice model that treats near-optimal configurations as valid targets, and a baseline single-label model.
Paweł Kolendo, Wojciech Chmiel, J. Kwiecien· International Conference on...· 0 citations
Findings indicate that while LLM-based performance prediction is not yet a reliable substitute for benchmarking, it shows potential as a complementary pre-screening tool in iterative algorithm design, particularly in settings where code modifications follow predictable patterns.
Michal Pluháček, Paweł Kolendo, Krzysztof Tylka-Suleja et al.· GECCO Companion· 0 citations
