Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Duan, Boyan, Liang, Xiao, Lu, Shuai, Wang, Yaoxiang, Shen, Yelong, Chang, Kai-Wei, Wu, Ying Nian, Yang, Mao, Chen, Weizhu, Gong, Yeyun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909933419626496
author Duan, Boyan
Liang, Xiao
Lu, Shuai
Wang, Yaoxiang
Shen, Yelong
Chang, Kai-Wei
Wu, Ying Nian
Yang, Mao
Chen, Weizhu
Gong, Yeyun
author_facet Duan, Boyan
Liang, Xiao
Lu, Shuai
Wang, Yaoxiang
Shen, Yelong
Chang, Kai-Wei
Wu, Ying Nian
Yang, Mao
Chen, Weizhu
Gong, Yeyun
contents Automated theorem proving in Euclidean geometry, particularly for International Mathematical Olympiad (IMO) level problems, remains a major challenge and an important research focus in Artificial Intelligence. In this paper, we present a highly efficient method for geometry theorem proving that runs entirely on CPUs without relying on neural network-based inference. Our initial study shows that a simple random strategy for adding auxiliary points can achieve silver-medal level human performance on IMO. Building on this, we propose HAGeo, a Heuristic-based method for adding Auxiliary constructions in Geometric deduction that solves 28 of 30 problems on the IMO-30 benchmark, achieving gold-medal level performance and surpassing AlphaGeometry, a competitive neural network-based approach, by a notable margin. To evaluate our method and existing approaches more comprehensively, we further construct HAGeo-409, a benchmark consisting of 409 geometry problems with human-assessed difficulty levels. Compared with the widely used IMO-30, our benchmark poses greater challenges and provides a more precise evaluation, setting a higher bar for geometry theorem proving.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00097
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions
Duan, Boyan
Liang, Xiao
Lu, Shuai
Wang, Yaoxiang
Shen, Yelong
Chang, Kai-Wei
Wu, Ying Nian
Yang, Mao
Chen, Weizhu
Gong, Yeyun
Artificial Intelligence
Computational Geometry
Automated theorem proving in Euclidean geometry, particularly for International Mathematical Olympiad (IMO) level problems, remains a major challenge and an important research focus in Artificial Intelligence. In this paper, we present a highly efficient method for geometry theorem proving that runs entirely on CPUs without relying on neural network-based inference. Our initial study shows that a simple random strategy for adding auxiliary points can achieve silver-medal level human performance on IMO. Building on this, we propose HAGeo, a Heuristic-based method for adding Auxiliary constructions in Geometric deduction that solves 28 of 30 problems on the IMO-30 benchmark, achieving gold-medal level performance and surpassing AlphaGeometry, a competitive neural network-based approach, by a notable margin. To evaluate our method and existing approaches more comprehensively, we further construct HAGeo-409, a benchmark consisting of 409 geometry problems with human-assessed difficulty levels. Compared with the widely used IMO-30, our benchmark poses greater challenges and provides a more precise evaluation, setting a higher bar for geometry theorem proving.
title Gold-Medal-Level Olympiad Geometry Solving with Efficient Heuristic Auxiliary Constructions
topic Artificial Intelligence
Computational Geometry
url https://arxiv.org/abs/2512.00097