Evolving Code with A Large Language Model

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@Misc{hemberg2024evolvingcodelargelanguage,

• author = "Erik Hemberg and Stephen Moskal and Una-May O'Reilly",
• title = "Evolving Code with A Large Language Model",
• year = "2024",
• howpublished = "arXiv",
• month = "13 " # jan,
• keywords = "genetic algorithms, genetic programming, ANN, Large Language Models, Evolutionary Algorithm, Operators, Code Llama Instruct, HumanEval, MBPP, APPS, MultiPL-E, GSM8Km, Tutorial-LLMGP",
• eprint = "2401.07102",
• archiveprefix = "arXiv",
• primaryclass = "cs.NE",
• URL = "https://arxiv.org/abs/2401.07102",
• size = "34 pages",
• abstract = "We present LLM GP, a formalised LLM-based evolutionary algorithm designed to evolve code. Like GP, it uses evolutionary operators, but its designs and implementations of those operators radically differ from GP because they enlist an LLM, using prompting and the LLMs pre-trained pattern matching and sequence completion capability. We also present a demonstration-level variant of LLM GP and share its code. By addressing algorithms that range from the formal to hands-on, we cover design and LLM-usage considerations as well as the scientific challenges that arise when using an LLM for genetic programming.",

}

Genetic Programming entries for Erik Hemberg Stephen Moskal Una-May O'Reilly

Citations