Skip to content

MechGeo: Autoformalizing and Proving Euclidean Geometry in Lean 4

Aug 2026 · arXiv.org · Vol abs/2608.02295 · 0 citations · 35 references
Computer Science

TL;DR

These results establish counterexample guided diagnosis, geometric reasoning, and certified symbolic computation as a practical foundation for trustworthy formal geometry.

Abstract

We present MechGeo, a Mathlib native agentic framework that jointly addresses faithful autoformalization and certified proof construction for Euclidean geometry. In this framework, GeoFormalizer represents informal problems in GeoIR, deterministically translates them into Lean 4, and iteratively repairs candidate statements using structural diagnostics and semantic evaluation. GeoProver constructs geometric proof plans, derives intermediate lemmas, and selectively algebraizes suitable subgoals through a library verified in Lean. Singular or SymPy may generate algebraic certificates, but all resulting proofs and counterexamples are checked by Lean's kernel. Experiments across seven LLM backbones show substantial improvements in autoformalization, particularly for models with weaker direct translation performance. On 43 historical IMO geometry problems, GeoFormalizer generates formal statements that GeoProver proves in 29 cases; for the remaining 14, it constructs counterexamples verified in Lean and proves all repaired statements after expert correction. Together with IMO 2026 Problem 2, this yields, to the best of our knowledge, the largest reported collection of automated, kernel-checked Lean proofs for IMO geometry problems. On the 14 geometry statements in LEAP's Lean-IMO-Bench, MechGeo proves 12 for the first time, formally refutes the remaining two, and proves both repaired statements. These results establish counterexample guided diagnosis, geometric reasoning, and certified symbolic computation as a practical foundation for trustworthy formal geometry.

View source

Similar papers

Review Sep 2026

Long-horizon autoformalization of a core theorem underlying MIP* = RE

Landmark mathematical formalizations have taken specialist teams years to complete. We present FormalFlow, a system that coordinates AI proving agents under human supervision to address statement drift and proof composition in long-horizon formalization. Drawing on software-engineering principles and practices, it uses...

Si-Rui Lu, Rui-Xuan Deng, Yan-Qiao Zhu et al. · 2 citations
#artificial intelligence Preprint Oct 2026

IneqAgent: Agentic Inequality Proving in Lean with Symbolic Computation

Formal inequality proving requires mathematical reasoning and exact computation, often connected through intermediate lemmas and goal reformulations. We introduce IneqAgent, an agentic framework combining LLM reasoning with symbolic computation for inequality proving in Lean4. Lemma-level Monte Carlo Tree Search coordi...

Gao-Lei He, Jin-Hui Li, Ruo-Bing Zuo et al. · 0 citations
#artificial intelligence Preprint Oct 2026

Algebraic World Model: From Exploration to Proofs

AI has made remarkable progress in mathematics, solving challenging problems with machine-checkable proofs in Lean, yet typically relying on predefined mathematical definitions and formal specifications. This raises a natural question: can it reason rigorously about an unknown world? We introduce the Algebraic World Mo...

Guan-Cheng Pan, Qi-Xin Tan, Yang Yuan et al. · 0 citations
Preprint Oct 2026

A Lean formalisation of the disproof of Ramaekers's conjecture

We describe Redhill, a Lean formalisation of the major results in H\"olzl, Kleine and Stephan's"Improved Lower Bounds for Strong $n$-Conjectures"(arXiv:2409.13439). Design decisions regarding types and data structures are justified as enabling canonical versions of the paper's claims, and from there the most direct pro...

Jeremy Tan · 0 citations
Preprint Oct 2026

Agent4FreeFem: A Verification-Guided Framework for Autonomous Topology Optimization

Topology optimization has become an indispensable design tool in the aerospace, automotive, and mechanical engineering industries. Yet bringing a new problem from its description to an optimized result remains slow, expert-dependent, and unreliable: the workflow spans many manually connected stages, each new problem re...

Zhi-Pu Cui, He-Lin Gong, Sheng-Feng Zhu · 0 citations
#artificial intelligence Preprint Oct 2026

VIGOR: Verifiable Industrial Geometry Optimization and Repair in Scene Programs

Large language models (LLMs) increasingly generate structured layouts and executable scene programs from natural-language instructions. However, executability does not imply engineering feasibility: an industrial scene program may execute successfully while its final state still violates coupled boundary, collision, cl...

Fu-Qiang Wang, Zheng Guo, Xiao-Ming Wu et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.