LeanGeo: Formalizing Competitional Geometry problems in Lean

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Song, Chendong, Wang, Zihan, Pu, Frederick, Wang, Haiming, Lin, Xiaohan, Liu, Junqi, Li, Jia, Liu, Zhengying
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866918127847079936
author Song, Chendong
Wang, Zihan
Pu, Frederick
Wang, Haiming
Lin, Xiaohan
Liu, Junqi
Li, Jia
Liu, Zhengying
author_facet Song, Chendong
Wang, Zihan
Pu, Frederick
Wang, Haiming
Lin, Xiaohan
Liu, Junqi
Li, Jia
Liu, Zhengying
contents Geometry problems are a crucial testbed for AI reasoning capabilities. Most existing geometry solving systems cannot express problems within a unified framework, thus are difficult to integrate with other mathematical fields. Besides, since most geometric proofs rely on intuitive diagrams, verifying geometry problems is particularly challenging. To address these gaps, we introduce LeanGeo, a unified formal system for formalizing and solving competition-level geometry problems within the Lean 4 theorem prover. LeanGeo features a comprehensive library of high-level geometric theorems with Lean's foundational logic, enabling rigorous proof verification and seamless integration with Mathlib. We also present LeanGeo-Bench, a formal geometry benchmark in LeanGeo, comprising problems from the International Mathematical Olympiad (IMO) and other advanced sources. Our evaluation demonstrates the capabilities and limitations of state-of-the-art Large Language Models on this benchmark, highlighting the need for further advancements in automated geometric reasoning. We open source the theorem library and the benchmark of LeanGeo at https://github.com/project-numina/LeanGeo/tree/master.
format Preprint
id arxiv_https___arxiv_org_abs_2508_14644
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle LeanGeo: Formalizing Competitional Geometry problems in Lean
Song, Chendong
Wang, Zihan
Pu, Frederick
Wang, Haiming
Lin, Xiaohan
Liu, Junqi
Li, Jia
Liu, Zhengying
Artificial Intelligence
Geometry problems are a crucial testbed for AI reasoning capabilities. Most existing geometry solving systems cannot express problems within a unified framework, thus are difficult to integrate with other mathematical fields. Besides, since most geometric proofs rely on intuitive diagrams, verifying geometry problems is particularly challenging. To address these gaps, we introduce LeanGeo, a unified formal system for formalizing and solving competition-level geometry problems within the Lean 4 theorem prover. LeanGeo features a comprehensive library of high-level geometric theorems with Lean's foundational logic, enabling rigorous proof verification and seamless integration with Mathlib. We also present LeanGeo-Bench, a formal geometry benchmark in LeanGeo, comprising problems from the International Mathematical Olympiad (IMO) and other advanced sources. Our evaluation demonstrates the capabilities and limitations of state-of-the-art Large Language Models on this benchmark, highlighting the need for further advancements in automated geometric reasoning. We open source the theorem library and the benchmark of LeanGeo at https://github.com/project-numina/LeanGeo/tree/master.
title LeanGeo: Formalizing Competitional Geometry problems in Lean
topic Artificial Intelligence
url https://arxiv.org/abs/2508.14644