AI improves precise mathematical constants with interpretable proof refinements
Improving Analytic Constants via Interpretable AI-Guided Lean Proof Refinement
Artificial IntelligenceMachine Learning
Summary
Some important numbers in math come from complicated proofs that are hard to improve. The authors use AI to carefully revise parts of these proofs without changing the big picture, making the final numbers more accurate. They represent the proofs in a way that people can follow and check, allowing AI updates to show exactly how improvements happen step by step. Their method improved two well-known constants, showing that AI can help discover better math results while keeping them understandable.
What this means in practice
- •For mathematical software developers: Use AI-guided partial proof formalization to automate tightening numerical bounds in formal verification tools.
- •For automated reasoning engineers: Incorporate interpretable AI agents that iteratively improve proof components while preserving dependency structures for stronger verified mathematical results.
Authors
Rahul Saha, Alan Li, Anton Xue, Swarat Chaudhuri, Adam Klivans, Pravesh K. Kothari, Raghu Meka
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 ($\mathcal{K}_G$), we obtain $$ \mathcal{K}_G \leq \fracπ{2\log(1+\sqrt{2})} - 10^{-17}, $$ an explicit numerical improvement over Krivine's 1977 bound. For Korenblum's constant ($\mathcal{K}_K$), we obtain $$ \mathcal{K}_K \geq 0.356565, $$ improving Wang's 2025 bound of $0.3554$. Our experiments demonstrate the potential of both partial formalization and iterative agentic refinement for interpretable mathematical discovery.