Matej Balog

Mathematical exploration and discovery at scale AlphaEvolve is a generic evolutionary coding agent that combines the generative capabilities of LLMs with automated evaluation in an iterative evolutionary framework that proposes, tests, and refines ...

A new paper with Bogdan Georgiev, Javier Gomez-Serrano, and Adam Zsolt Wagner: "Mathematical exploration and discovery at scale" arxiv.org/abs/2511.02864. Further discussion is at terrytao.wordpress.com/2025/11/05/m...

Google DeepMind’s new AI uses large language models to crack real-world problems AlphaEvolve finds new algorithms that outperform the best human-made solutions for data center management, chip design and more.

AlphaEvolve finds new algorithms that outperform the best human-made solutions for data center management, chip design and more.

AlphaEvolve was developed by our wonderful team working on AI for algorithm discovery.

On BlueSky: @emidup.bsky.social @swarat.bsky.social

We’ve only scratched the surface of possible use cases of AlphaEvolve

I’m looking forward to many more applications across the sciences and computational problems

AlphaEvolve advanced over 10 open problems across Maths. But one is particularly precious to me:

It found the first improvement after 56 years to how fast we can multiply 4x4 matrices 🤯 (with complex number entries)

And it did so by discovering a sophisticated search algorithm

AlphaEvolve: A Gemini-powered coding agent for designing advanced algorithms New AI agent evolves algorithms for math and practical applications in computing by combining the creativity of large language models with automated evaluators

Announcing AlphaEvolve, our new LLM coding agent that has
- made new scientific discoveries
- discovered algorithms that are now deployed at Google (in Gemini, Transformers, TPU hardware design & data centers)

Blog: deepmind.google/discover/blo...
White paper:
storage.googleapis.com/deepmind-med...

We introduce 🌸✨ AlphaEvolve ✨🌸, an evolutionary coding agent using LLMs coupled with automatic evaluators, to tackle open scientific problems 🧑‍🔬 and optimize critical pieces of compute infra ⚙️

deepmind.google/discover/blo...

Also not the first time (nor the last) that DeepMind has improved a component of quantum computers! arxiv.org/abs/2402.14396

Great work, congratulations to both teams!

Despite a massive head start, BlueSky has now overtaken Threads in the US 👇