2025-11-07
We tested AlphaEvolve on a wide-ranging portfolio of 67 mathematical problems in combinatorics, geometry and more. It found new constructions that improved upon the best-known results on about 20 of them, such as finding denser ways to pack 11 cubes into a larger cube. [image]
@azwagner_
Researchers tested Google DeepMind's AlphaEvolve AI coding agent on 67 mathematical problems and found that it discovered improved solutions to ~20 of them
Really happy to share our new paper on using AlphaEvolve for mathematical exploration at scale, written with Javier Gómez-Serrano, Terence Tao, and @GoogleDeepMind's Bogdan Georgie...
2025-05-14
I'm happy to share our new white paper on AlphaEvolve, an evolutionary coding agent. It uses Large Language Models to discover and optimize complex algorithms, aiming to tackle challenging computational and scientific problems by iteratively improving code. [image]
Google DeepMind
Google DeepMind unveils AlphaEvolve, a Gemini-powered AI coding agent that designs and optimizes advanced algorithms using an evolutionary framework
New AI agent evolves algorithms for math and practical applications in computing by combining the creativity of large language models with automated evaluators