[HN Gopher] OpenEvolve: Teaching LLMs to Discover Algorithms Thr...
       ___________________________________________________________________
        
       OpenEvolve: Teaching LLMs to Discover Algorithms Through Evolution
        
       Author : codelion
       Score  : 41 points
       Date   : 2025-12-09 22:54 UTC (11 hours ago)
        
 (HTM) web link (algorithmicsuperintelligence.ai)
 (TXT) w3m dump (algorithmicsuperintelligence.ai)
        
       | jasonjmcghee wrote:
       | 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)
        
         | gerdesj wrote:
         | 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.
        
         | jasonb05 wrote:
         | 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
        
       | DoctorOetker wrote:
       | Very interesting that the LLM weights are co-evolved and
       | reasoning skills improve!
        
         | viraptor wrote:
         | 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?
        
       | N_Lens wrote:
       | 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 wrote:
       | Sakana.ai improved on this by honing in on sample efficiency iirc
       | with shinkaevolve (which is open source and not an ai slop
       | project)
        
         | jasonb05 wrote:
         | Yep, ShinkaEvolve described here: https://sakana.ai/shinka-
         | evolve/ and available here:
         | https://github.com/SakanaAI/ShinkaEvolve
        
       ___________________________________________________________________
       (page generated 2025-12-10 10:01 UTC)