An AI-Assisted Formalization of the Poincar'e Conjecture
cs.AI, math.GT
Submitted: 2026-10-06
Updated: 2026-10-06
Comments: 15 pages, 2 figures. Code: https://github.com/frenzymath/PoincareConjecture
Code: https://github.com/frenzymath/PoincareConjecture
Project page: https://frenzymath.github.io/Poincare-Conjecture/#
License: http://creativecommons.org/licenses/by/4.0/
The gist: We present an AI-assisted Lean 4 formalization of the Poincaré conjecture.
Abstract
We present an AI-assisted Lean 4 formalization of the Poincaré conjecture. The project began with limited reusable formal infrastructure for the geometric analysis behind the proof. To organize this work, we combined a proof blueprint prepared by mathematicians with explicit milestone statements. These milestones enabled parallel agent work and gave mathematicians clear points to locate blockers and provide effective mathematical guidance. Our analysis identifies the human interventions and organizational choices behind this workflow. The project provides a starting point toward reusable infrastructure for future formalization projects; such infrastructure, once developed, could eventually reduce the cost of verifying mathematical results in geometric analysis.
Sources
- Formalization of De Giorgi--Nash--Moser Theory in Lean
- Prove2Me: An Open Collaborative Platform for Scaling Math Formalization
- Automatic Textbook Formalization
- Multilingual Mathematical Autoformalization
- Automated Conjecture Resolution with Formal Verification
- Notes on Perelman's papers
- Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics
- Correction to Section 19.2 of Ricci Flow and the Poincare Conjecture
- The entropy formula for the Ricci flow and its geometric applications
- Ricci flow with surgery on three-manifolds
- Finite extinction time for the solutions to the Ricci flow on certain three-manifolds
- Generative Language Modeling for Automated Theorem Proving
- DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decomposition
- 130k Lines of Formal Topology in Two Weeks: Simple and Cheap Autoformalization for Everyone?
- First Experiments with Neural Translation of Informal to Formal Mathematics
- M2F: Automated Formalization of Mathematical Literature at Scale
- Autoformalization with Large Language Models
- LeanDojo: Theorem Proving with Retrieval-Augmented Language Models
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Agents' Last Exam
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems