coding

AlphaEvolve

by Google DeepMind

AlphaEvolve is a Gemini-powered evolutionary coding agent developed by Google DeepMind that uses LLMs to mutate, recombine, and evolve algorithm code, with each candidate evaluated against automated verifiers in a closed loop. It functions as a meta-algorithm — autonomously generating and refining search algorithms for combinatorial optimization problems at scales beyond human intuition. Since its unveiling in May 2025, it has produced state-of-the-art breakthroughs in matrix multiplication, kissing number bounds, Ramsey theory, data center scheduling, and TPU circuit design.

7 Overall Score

Scores

Capability
9
Ease of Use
2
Documentation
5
Reliability
8
Value
9
Momentum
8

Details

Status
active
Pricing
free
Launch Date
2025-05
Last Updated
2026-03-15

Key Features

  • LLM-driven code mutation and evolutionary recombination over algorithm space
  • Automated correctness verifiers provide fitness signal without human labelling
  • Meta-algorithm design — discovers novel search algorithms for hard combinatorial problems
  • Applied across domains: matrix multiplication records, TPU layout, data-center scheduling, Ramsey numbers
  • Parallelised island-model evolution scales across thousands of candidate programs simultaneously

Tech Stack

PythonGemini (Flash + Pro)Evolutionary AlgorithmsAutomated Code EvaluationFunSearch-derived Architecture