Why Agentic Theorem Prover Works: A Statistical Provability Theory of Mathematical Reasoning Models

ArXi:2602.10538v3 Announce Type: replace-cross Agentic theorem provers combine a reasoning model, retrieval, search, and a proof assistant verifier, yet it remains unclear which components actually improve finite-budget proof success and why they help on real mathematical workloads. We study this question through statistical provability: the probability of reaching a verified proof within a budget on a specified stream of theorem instances.