Thomas Gabor

Towards Variation via Foundation Model: An Empirical Study of a Problem-Agnostic No-Code LLM-Guided Evolutionary Algorithm

The natural-language-based genetic algorithm (NaLaGA) shows that a generic, problem-independent genetic algorithm (GA) can function by utilizing large language models (LLMs) for all interactions with the solution candidates without ever running any LLM-generated code. We analyze inherent biases in the function of a NaLaGA approach from prior work and propose some architectural changes to increase its generalizability.