Proving mathematical theorems at the olympiad level represents a notable milestone in
human-level automated reasoning,,–, owing to their reputed difficulty among the world's best …

AI is undergoing a paradigm shift with the rise of models (eg, BERT, DALL-E, GPT-3) that are
trained on broad data at scale and are adaptable to a wide range of downstream tasks. We …

We explore the use of expert iteration in the context of language modeling applied to formal
mathematics. We show that at same compute budget, expert iteration, by which we mean …

We propose a novel approach to interactive theorem-proving (ITP) using deep reinforcement
learning. The proposed framework is able to learn proof search strategies as well as tactic …

Traditional automated theorem proving systems for first-order logic depend on speed-
optimized search and many handcrafted heuristics designed to work over a wide range of …

Theorem proving is a fundamental aspect of mathematics, spanning from informal reasoning
in mathematical language to rigorous derivations in formal systems. In recent years, the …

Mathematics olympiads are prestigious competitions, with problem proposing and solving
highly honored. Building artificial intelligence that proposes and solves olympiads presents …

With artificial intelligence (AI) being well established within the daily lives of research
communities, we turn our gaze toward an application area that appears intuitively unsuited …

Imitation learning for the task of theorem proving is bottlenecked by the limited size of
existing libraries of formalized mathematics (eg mathlib [1]). Prior work utilizing language …

Existing approaches to learning to prove theorems focus on particular logics and datasets. In
this work, we propose Monte-Carlo simulations guided by reinforcement learning that can …