FunSearch

FunSearch
DeveloperGoogle DeepMind
ReleaseDecember 14, 2023 (2023-12-14)
Written inPython
TypeArtificial intelligence
program synthesis
evolutionary computation
mathematical optimization
LicenseApache License 2.0 (software)
CC BY 4.0 (other materials)
Websitedeepmind.google/discover/blog/funsearch-making-new-discoveries-in-mathematical-sciences-using-large-language-models/
Repositorygithub.com/google-deepmind/funsearch

FunSearch (short for searching in the function space) is an artificial intelligence method developed by Google DeepMind for discovering computer programs that solve mathematical and algorithmic problems. It combines a large language model with an automated evaluator and an evolutionary search procedure, generating candidate programs, scoring them, and using high-performing programs to produce new candidates.

Google DeepMind announced FunSearch in 2023, and the associated paper was published in Nature. The system was applied to the cap set problem in extremal combinatorics and to the online bin packing problem, where it found new mathematical constructions and new packing heuristics.