AlphaEvolve is an
evolutionary
Evolution is the change in the heritable characteristics of biological populations over successive generations. It occurs when evolutionary processes such as natural selection and genetic drift act on genetic variation, resulting in certa ...
coding agent for designing advanced
algorithms
In mathematics and computer science, an algorithm () is a finite sequence of mathematically rigorous instructions, typically used to solve a class of specific problems or to perform a computation. Algorithms are used as specifications for per ...
based on
large language models
A large language model (LLM) is a language model trained with Self-supervised learning, self-supervised machine learning on a vast amount of text, designed for natural language processing tasks, especially Natural language generation, language g ...
such as
Gemini. It was developed by
Google DeepMind
DeepMind Technologies Limited, trading as Google DeepMind or simply DeepMind, is a British–American artificial intelligence research laboratory which serves as a subsidiary of Alphabet Inc. Founded in the UK in 2010, it was acquired by Goo ...
and unveiled in May 2025.
Design
AlphaEvolve aims to autonomously discover and refine algorithms through a combination of
large language models
A large language model (LLM) is a language model trained with Self-supervised learning, self-supervised machine learning on a vast amount of text, designed for natural language processing tasks, especially Natural language generation, language g ...
(LLMs) and evolutionary computation.
AlphaEvolve needs an evaluation function with metrics to optimize, and an initial algorithm. At each step, AlphaEvolve uses the LLM to produce variants of the existing algorithms, and then selects the most effective ones.
Unlike domain-specific predecessors like
AlphaFold or
AlphaTensor
Because matrix multiplication is such a central operation in many numerical algorithms, much work has been invested in making matrix multiplication algorithms efficient. Applications of matrix multiplication in computational problems are found in m ...
, AlphaEvolve is designed as a general-purpose system. It can operate across a wide array of scientific and engineering tasks by automatically modifying code and optimizing for multiple objectives. Its architecture allows it to evaluate code programmatically, reducing reliance on human input and mitigating risks such as hallucinations common in standard LLM outputs.
Achievements
According to Google, across a selection of 50 open
mathematical problems
A mathematical problem is a problem that can be Representation (mathematics), represented, analyzed, and possibly solved, with the methods of mathematics. This can be a real-world problem, such as computing the Orbit#Planetary orbits, orbits of the ...
, the model was able to rediscover state-of-the-art solutions 75% of the time and discovered improved solutions 20% of the time, for example advancing the
kissing number problem.
AlphaEvolve was also used to optimize Google's computing ecosystem. Improved data center scheduling heuristics, enabled the recovery of 0.7% of stranded resources. It was also used to optimize
TPU circuit design and
Gemini's training
matrix multiplication
In mathematics, specifically in linear algebra, matrix multiplication is a binary operation that produces a matrix (mathematics), matrix from two matrices. For matrix multiplication, the number of columns in the first matrix must be equal to the n ...
kernel.
See also
*
Gemini (chatbot)
Gemini, formerly known as Bard, is a generative artificial intelligence chatbot developed by Google. Based on the large language model (LLM) Gemini (language model), of the same name, it was launched in 2023 in response to the rise of OpenAI' ...
*
Strassen algorithm
References
{{reflist
External links
AlphaEvolve white paper
Applied machine learning
2025 software
Google DeepMind