Solving Olympiad-level mathematical problems represents a significant advancement in machine intelligence and automated reasoning. Current machine learning methods, however, struggle to solve Olympiad-level problems beyond Euclidean plane geometry due to a lack of large-scale, high-quality datasets. The challenge is even greater in algebraic systems, which involve infinite reasoning spaces within finite conditions. To address these issues, we propose AIPS, an Algebraic Inequality Proving System capable of autonomously generating complex inequality theorems and effectively solving Olympiad-level inequality problems without requiring human demonstrations. During proof search in a mixed reasoning manner, a value curriculum learning strategy on generated datasets is implemented to improve proving performance, demonstrating strong mathematical intuitions. On a test set of 20 International Mathematical Olympiad-level inequality problems, AIPS successfully solved 10, outperforming state-of-the-art methods. Furthermore, AIPS automatically generated a vast array of non-trivial theorems without human intervention, some of which have been evaluated by professional contestants and deemed to reach the level of the International Mathematical Olympiad. Notably, one theorem was selected as a competition problem in a major city 2024 Mathematical Olympiad.
OptProver: Bridging Olympiad and Optimization through Continual Training in Formal Theorem Proving
School of Mathematical Sciences, Peking University(北京大学数学科学学院);Huawei Technologies(华为技术有限公司);Center for Machine Learning Research, Peking University(北京大学机器学习研究中心);Beijing International Center for Mathematical Research, Peking University(北京国际数学研究中心)
Proposing and solving olympiad geometry with guided tree search
Beijing Institute for General Artificial Intelligence (BIGAI)(北京通用人工智能研究院(BIGAI));Institute for Artificial Intelligence, Peking University(北京大学人工智能研究院)
FIMO: A Challenge Formal Dataset for Automated Theorem Proving
Peking University(北京大学);Huawei HiSilicon(华为海思);Sun Yat-sen University(中山大学);Huawei Noah’s Ark Lab(华为诺亚方舟实验室);The Chinese University of Hong Kong(香港中文大学)
UC Berkeley(伯克利大学);Brown University(布朗大学);Yonsei University(延世大学);Concordia University(Concordia 大学);Korea Institute for Advanced Study(韩国高级研究院);UC San Diego(圣地亚哥大学);Caltech(加州理工学院)