---
id: "2025-05-14-alphaevolve"
url: "https://postcutoff.com/e/2025-05-14-alphaevolve/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2025-05-14"
date_precision: day
category: science
importance: 4
confidence: high
status: [Result confirmed]
verification: Expert-checked
sources: 4
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2025-05-14-alphaevolve/

# AlphaEvolve: Gemini-powered agent discovers new algorithms

Google DeepMind's AlphaEvolve combined Gemini models with evolutionary search and automated evaluation to discover new algorithms, including a way to multiply 4×4 complex matrices with 48 scalar multiplications, improving on Strassen's 1969 algorithm.

## Key facts
- Announced 14 May 2025
- 4×4 complex-valued matrix multiplication with 48 scalar multiplications
- Matched state of the art on ~75% and improved on ~20% of 50+ open math problems tested, per DeepMind
- A scheduling heuristic recovers on average 0.7% of Google's worldwide compute resources
- Kissing number in 11 dimensions: lower bound raised from 592 to 593
- The 48-multiplication result is for complex-valued, non-commutative 4×4 multiplication; a June 2025 human follow-up gave a 48-multiplication scheme with rational coefficients (arXiv 2506.13242)
- Nov 2025: Georgiev, Gómez-Serrano, Tao and Wagner applied AlphaEvolve to 67 problems (see related entry)

## What happened

DeepMind described an agent that iteratively writes and evaluates code, already deployed across Google's data centers, chip design and AI training.

## Why it matters

A concrete example of LLM-based systems making novel discoveries and improving the infrastructure that trains them — an early form of recursive improvement.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms (Google DeepMind)](https://deepmind.google/discover/blog/alphaevolve-a-gemini-powered-coding-agent-for-designing-advanced-algorithms/) (deepmind.google, official)
2. [AlphaEvolve: A coding agent for scientific and algorithmic discovery (arXiv)](https://arxiv.org/abs/2506.13131) (arxiv.org, paper)
3. [Independent verification of the 48-multiplication algorithm (GitHub)](https://github.com/PhialsBasement/AlphaEvolve-MatrixMul-Verification) (github.com, code)
4. [Human follow-up: 48 multiplications with rational coefficients (arXiv 2506.13242)](https://arxiv.org/abs/2506.13242) (arxiv.org, paper)

## Changes

- 2026-09-29: Added science block, kissing-number fact, verification links
- 2026-09-29 (filed): Created

## Related

- 2025-11-05: [Tao, Gómez-Serrano, Georgiev and Wagner test AlphaEvolve on 67 maths problems](https://postcutoff.com/e/2025-11-05-alphaevolve-tao-67-problems/index.md)
- 2024-07-25: [AlphaProof and AlphaGeometry 2 reach IMO silver-medal standard](https://postcutoff.com/e/2024-07-25-alphaproof-imo-silver/index.md)
- 2023-12-14: [FunSearch: an LLM finds new cap-set constructions, the first LLM discovery in open maths](https://postcutoff.com/e/2023-12-14-funsearch-cap-sets/index.md)
- 2022-10-05: [AlphaTensor discovers faster matrix multiplication algorithms, beating Strassen's 1969 record for 4×4 mod 2](https://postcutoff.com/e/2022-10-05-alphatensor-matrix-multiplication/index.md)