https://openreview.net/forum?id=7B8AYtmQRT&referrer=%5Bthe%20profile%20of%20Hongzhou%20Lin%5D(%2Fprofile%3Fid%3D~Hongzhou_Lin1)
LLM-based formal proof assistants (e.g., in Lean) hold great promise for automating mathematical discovery. But beyond syntactic correctness, do these systems...
compbenchmarkinghumanintuitivereasoning