cs.AINov 7, 2026

Improving Analytic Constants via Interpretable AI-Guided Lean Proof Refinement

Authors: Rahul Saha, Alan Li, Anton Xue, Swarat Chaudhuri, Adam Klivans, Pravesh K. Kothari, Raghu Meka

Organizations: UT Austin · Princeton University · UCLA

Abstract

AI agents are increasingly capable of discovering new mathematical results, yet their reasoning and generated proofs can be difficult to understand and verify. We introduce an interpretable framework for AI-guided mathematical discovery, focused on improving quantitative bounds on analytic constants. Our key insight is that existing proofs often contain slack in intermediate lemmas, which can be tightened without reconstructing the entire argument. To exploit this structure, we represent proofs as partially-formalized Lean blueprints: human-interpretable dependency graphs of definitions, lemmas, and theorems. An AI agent then iteratively refines the Lean code while preserving the blueprint's dependency structure, allowing local improvements to automatically propagate to a verified final bound. This interpretable structure allows humans to inspect the agent's refinements and understand how local improvements propagate to the final theorem. For Grothendieck's constant (KG\mathcal{K}_G), we obtain KG≤π2log⁡(1+2)−10−17,\mathcal{K}_G \leq \fracπ{2\log(1+\sqrt{2})} - 10^{-17}, an explicit numerical improvement over Krivine's 1977 bound. For Korenblum's constant (KK\mathcal{K}_K), we obtain KK≥0.356565,\mathcal{K}_K \geq 0.356565, improving Wang's 2025 bound of 0.35540.3554. Our experiments demonstrate the potential of both partial formalization and iterative agentic refinement for interpretable mathematical discovery.

Figures & tables

Appendix figures & tables10 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. LeanDojo-v2: A Comprehensive Library for AI-Assisted Theorem Proving in Lean

    Nov 6, 2026Ryan Hsiang, William Adkisson, Robert Joseph George +1Lean Theorem ProvingLarge Language Model-Guided Theorem Proving

  2. Advancing Mathematics Research with AI-Driven Formal Proof Search

    May 21, 2026George Tsoukalas, Anton Kovsharov, Sergey Shirobokov +18Large Language Model-Guided Theorem ProvingAutomated Theorem Proving