Very interesting that the LLM weights are co-evolved and reasoning skills improve!
viraptor 5 days 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?
DoctorOetker 5 days ago [-]
you are correct, on re-reading they only evolved the prompts ...
N_Lens 5 days 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.
quantbagel 5 days 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)
Though I'm not sure the public can access AlphaEvolve yet.
(https://arxiv.org/abs/2506.13131)
At the moment I'm mildly skeptical and uncertain of whether to twist or stick.
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
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.