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

Agentic theorem provers -- pipelines that couple a mathematical reasoning model with library retrieval, subgoal-decomposition/search planner, and a proof assistant verifier -- have recently achieved striking empirical success, yet it remains unclear which components drive performance and why such systems work at all despite classical hardness of proof search. We propose a distributional viewpoint and introduce \textbf{statistical provability}, defined as the finite-horizon success probability of reaching a verified proof, averaged over an instance distribution, and formalize modern theorem-proving pipelines as time-bounded MDPs. Exploiting Bellman structure, we prove existence of optimal policies under mild regularity, derive provability certificates via sub-/super-solution inequalities, and bound the performance gap of score-guided planning (greedy/top-\(k\)/beam/rollouts) in terms of approximation error, sequential statistical complexity, representation geometry (metric entropy/doubling structure), and action-gap margin tails. Together, our theory provides a principled, component-sensitive explanation of when and why agentic theorem provers succeed on biased real-world problem distributions, while clarifying limitations in worst-case or adversarial regimes.

Don't Eliminate Cut: Exponential Separations in LLM-Based Theorem Proving

We develop a theoretical analysis of LLM-guided formal theorem proving in interactive proof assistants (e.g., Lean) by modeling tactic proposal as a stochastic policy in a finite-horizon deterministic MDP. To capture modern representation learning, we treat the state and action spaces as general compact metric spaces and assume Lipschitz policies. To explain the gap between worst-case hardness and empirical success, we introduce problem distributions generated by a reference policy $q$, including a latent-variable model in which proofs exhibit reusable cut/lemma/sketch structure represented by a proof DAG. Under a top-$k$ search protocol and Tsybakov-type margin conditions, we derive lower bounds on finite-horizon success probability that decompose into search and learning terms, with learning controlled by sequential Rademacher/covering complexity. Our main separation result shows that when cut elimination expands a DAG of depth $D$ into a cut-free tree of size $Ω(Λ^D)$ while the cut-aware hierarchical process has size $O(λ^D)$ with $λ\llΛ$, a flat (cut-free) learner provably requires exponentially more data than a cut-aware hierarchical learner. This provides a principled justification for subgoal decomposition in recent agentic theorem provers.