OpenEvolve: Teaching LLMs to Discover Algorithms Through Evolution (opens in new tab)

(algorithmicsuperintelligence.ai)

53 pointscodelion3mo ago9 comments

9 comments

jasonjmcghee3mo 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)

gerdesj3mo 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.

jasonb053mo 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

DoctorOetker3mo ago

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

viraptor3mo 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?

DoctorOetker3mo ago

you are correct, on re-reading they only evolved the prompts ...

N_Lens3mo 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.

quantbagel3mo 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)

jasonb053mo ago

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

j / k navigate · click thread line to collapse

9 comments

jasonjmcghee3mo 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)

gerdesj3mo 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.

jasonb053mo 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

DoctorOetker3mo ago

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

viraptor3mo 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?

DoctorOetker3mo ago

you are correct, on re-reading they only evolved the prompts ...

N_Lens3mo ago

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

quantbagel3mo 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)

jasonb053mo ago

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

j / k navigate · click thread line to collapse