Large Language Model-Based Evolutionary Optimizer: Reasoning with elitism
This addresses the challenge of applying LLMs to optimization tasks for researchers and engineers, though it is incremental as it builds on existing LLM capabilities with a novel method.
The paper tackles the problem of using large language models (LLMs) as black-box optimizers for numerical optimization, introducing the Language-Model-Based Evolutionary Optimizer (LEO) and showing it yields comparable results to state-of-the-art methods on benchmarks and industrial problems like supersonic nozzle shape optimization.
Large Language Models (LLMs) have demonstrated remarkable reasoning abilities, prompting interest in their application as black-box optimizers. This paper asserts that LLMs possess the capability for zero-shot optimization across diverse scenarios, including multi-objective and high-dimensional problems. We introduce a novel population-based method for numerical optimization using LLMs called Language-Model-Based Evolutionary Optimizer (LEO). Our hypothesis is supported through numerical examples, spanning benchmark and industrial engineering problems such as supersonic nozzle shape optimization, heat transfer, and windfarm layout optimization. We compare our method to several gradient-based and gradient-free optimization approaches. While LLMs yield comparable results to state-of-the-art methods, their imaginative nature and propensity to hallucinate demand careful handling. We provide practical guidelines for obtaining reliable answers from LLMs and discuss method limitations and potential research directions.