Imagen de Portada

Large language models help programs to evolve

Guardado en:
Publicado en:Nature vol. 625, no. 7995 (Jan 18, 2024), p. 452
Autor principal: Mouret, Jean-Baptiste
Publicado:
Nature Publishing Group
Materias:
Programming languages
Computers
Python
Computer science
Large language models
Genetic algorithms
Artificial intelligence
Syntax
Mathematical models
Programmers
Social
Acceso en línea:Citation/Abstract
Full Text
Full Text - PDF
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:Usingthis representation, a genetic-programming system 'mutates' a program by randomly changing one node in the tree to a different value (Fig. la). Instead of replacing random parts of a syntax tree, an LLM can generate a variation of a program written in a standard programming language, such as Python. To do so, a simple, but powerful, approach is to select two programs, concatenate them, and ask the LLM to complete the program using the concatenated pair as a prompt - resulting in the generation of a third program (Fig. 1b). Romera-Paredes et al. used this fresh approach to genetic programming to find ways of solving mathematical problems in optimization and geometry that were better than the best attempts of human programmers.
ISSN:0028-0836
1476-4687
DOI:10.1038/d41586-023-03998-0
Fuente:Science Database