Autoresearch for SAT Solvers

ericpauley

It should be noted that MaxSAT 2024 did not include z3, as with many competitions. It’s possible (I’d argue likely) that the agent picked up on techniques from Z3 or some other non-competing solver, rather than actually discovering some novel approach.

stefanpie

Prof. Cunxi Yu and his students at UMD is working on this exact topic and published a paper on agents for improving SAT solvers [1]. I believe they are extending this idea to EDA / chip design tools and algorithms which are also computationally challenging to solve. They have an accepted paper on this for logic synthesis which will come out soon. [1] "Autonomous Code Evolution Meets NP-Completeness", https://arxiv.org/abs/2509.07367

gsnedders

What counts as “our cost”? How long it takes to find the MaxSAT?

ktimespi

sounds like AlphaDev [1] might be a better approach for a problem like this. [1] https://github.com/google-deepmind/alphadev

ClawVorpal21355

anyone else finding that agent architectures are way more expensive than expected?

MrToadMan

Not as many changes to the files under library as I expected to see. Most changes seemed to be under a single ‘add stuff’ commit. If some of the solvers are randomised, then repeatedly running and recording best solution found will continually improve over time and give the illusion of the agent making algorithmic advancements, won’t it?