OpenEvolve: Teaching LLMs to Discover Algorithms Through Evolution

Posted by codelion 8 hours ago

378Original

Comments

Comment by jasonjmcghee 7 hours ago

It doesn't mention it in the article, but guessing this is based on / inspired by AlphaEvolve?

Though I'm not sure the public can access AlphaEvolve yet.

(https://arxiv.org/abs/2506.13131)

Comment by jasonb05 1 hour ago

Agreed, not mentioned.

Nevertheless, I see a link to github for the OpenEvolve project [1] that in turn states:

> Open-source implementation of AlphaEvolve

[1] https://github.com/algorithmicsuperintelligence/openevolve

Comment by gerdesj 6 hours ago

If AlphaEvolve is: "a quality-diversity search framework for algorithm discovery" then maybe.

At the moment I'm mildly skeptical and uncertain of whether to twist or stick.

Comment by DoctorOetker 6 hours ago

Very interesting that the LLM weights are co-evolved and reasoning skills improve!

Comment by viraptor 58 minutes ago

What do you mean by this? I can't find anything there about modifying the used LLMs and the hosted ones wouldn't be possible to change. Do I misunderstand the convolved part you mentioned?

Comment by N_Lens 6 hours ago

Some cool optimisations here: MAP elites, island models to prevent premature convergence & fast rejection of bad candidates.

What's particularly interesting is the meta level insight: The system discovered scipy.optimize.SLSQP for circle packing - a completely different algorithmic paradigm than it started with. It's genuinely discovering new approaches, not just parameter-tuning.

Comment by quantbagel 6 hours ago

Sakana.ai improved on this by honing in on sample efficiency iirc with shinkaevolve (which is open source and not an ai slop project)

Comment by jasonb05 1 hour ago

Yep, ShinkaEvolve described here: https://sakana.ai/shinka-evolve/ and available here: https://github.com/SakanaAI/ShinkaEvolve