LLM Guided Evolution - The Automation of Models Advancing Models

arXiv:2403.11446v1 Announce Type: cross
Abstract: In the realm of machine learning, traditional model development and automated approaches like AutoML typically rely on layers of abstraction, such as tree-based or Cartesian genetic programming. Our study introduces "Guided Evolution" (GE), a novel framework that diverges from these methods by utilizing Large Language Models (LLMs) to directly modify code. GE leverages LLMs for a more intelligent, supervised evolutionary process, guiding mutations and crossovers. Our unique "Evolution of Thought" (EoT) technique further enhances GE …

abstract abstraction arxiv automated automation automl cs.lg cs.ne development evolution framework genetic programming language large language llm machine machine learning model development novel programming study tree type