LLMs with evolutionary harnesses can dramatically improve scientific discovery through sample-efficient, iterative stepping-stone accumulation.
Robert Lange explains how evolutionary LLM-driven methods like Shinka Evolve cut costs and evaluation time, making scientific discovery more democratically accessible. ✦ AI generated
Robert Lange · Machine Learning Street Talk · 2026-03-13 · original ↗
starts at this moment · 4:24
“Tell me about the paper.”
One thing that sort of is important about sort of using all of these evolutionary LLM driven methods is sample efficiency, right? So, and many of these systems sample like let's say a thousand programs for a given task and what we tried to do with Shinka Evolve was try to essentially cut down costs as well as sort of computation evaluation time by introducing a set of sort of technical innovations to this evolutionary search
verbatim transcript · starts at 4:24
4:11don't do. Tell me about the paper. >> First off, of course, this was partially inspired by Alpha Evolve. I think it's great work. I know Alex and Matei and I think they were doing incredible science. One thing that sort of is important about sort of using all of these evolutionary LLM driven methods is sample efficiency, right? So, and many of these systems sample like let's say a
4:31thousand programs for a given task and what we tried to do with Shinka Evolve was try to essentially cut down costs as well as sort of computation evaluation time by introducing a set of sort of technical innovations to this evolutionary search and we showed that it's possible with very few program evaluations to basically improve upon like for example the circle packing canonical result that they showed in
4:56their paper. And yeah, more generally speaking, I think we're right now at a point or like at an inflection point where these sort of let's say evolutionary driven LLM systems can really revolutionize scientific discovery and yeah, we hope to have made a step forward to making this more democratically accessible, right? So, the code is open source available and yeah, by its sample efficient nature, we hope that many people can
5:24interact with the system and can make their own scientific discoveries as well. >> Yeah, that's actually a really important point because I suppose we can use these foundation models. And first of all, isn't it just fascinating to reflect that we have these amazing models out there that we can access so like GPT-5 and Grok-4 and they are so much better when you get them to refine their
5:45solution in in several steps. Why is that? I mean, I suppose a naive question would be why why aren't they just good out of the box? >> Potentially, like with enough random samples, right? It's sort of this monkey typing on the keyboard. Um they would potentially be able to get there, right? Um but in principle, it's sort of coming back to the principles of evolution, right? In the sense that you need to
6:08collect a bunch of stepping stones first and then build on top of them to to really find um innovations or to tune innovations down the line. And I think language models with the right sort of evolutionary harness are extremely powerful in terms of scaling up to um to to make discoveries. And um yeah, I think Jeremy, as well as the Alpha Evolve paper, as well as sort of work