arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2404.06405cs.AIcs.CGcs.CLcs.LG
收藏

吴方法可推动符号AI在IMO几何竞赛中匹敌银牌选手,助力AlphaGeometry超越金牌选手

Wu's Method can Boost Symbolic AI to Rival Silver Medalists and AlphaGeometry to Outperform Gold Medalists at IMO Geometry

IIIT Hyderabad(印度信息技术研究所海得拉巴分校);Tübingen AI Center, University of Tübingen(蒂宾根大学蒂宾根人工智能中心);University of Cambridge(剑桥大学)

Shiven Sinha, Ameya Prabhu, Ponnurangam Kumaraguru, Siddharth Bhat, Matthias Bethge

AI总结:

该研究重新评估吴方法在IMO几何题上的能力,发现其与经典合成方法结合可匹敌银牌选手,与AlphaGeometry结合后解题量达27/30,首次超越IMO金牌选手水平。

摘要:

几何定理证明是兼具直觉与逻辑能力的视觉推理的标志性任务。因此,奥林匹克级别几何题的自动定理证明被视为人机级自动推理领域的重要里程碑。AlphaGeometry作为一个基于1亿个合成样本训练的神经符号模型,其问世标志着一项重大突破。它解决了30道国际数学奥林匹克(IMO)题目中的25道,而据报道基于吴方法的基线仅能解决10道。在本研究简报中,我们重新审视了随AlphaGeometry一同提出的IMO-AG-30挑战赛,发现吴方法的实力出人意料。仅使用吴方法就能解决15道题,其中部分题目是其他任何方法都无法解答的。这带来了两项关键发现:(i)将吴方法与演绎数据库、角度/比例/距离追踪等经典合成方法相结合,仅使用一台纯CPU笔记本电脑、每道题限时5分钟的条件下,就能解决30道题中的21道。本质上,这一经典方法的解题量仅比AlphaGeometry少4道,并且确立了首个足以匹敌IMO银牌选手表现的全符号基线。(ii)在AlphaGeometry未能解决的5道题中,吴方法甚至能解决其中2道。因此,通过将AlphaGeometry与吴方法相结合,我们在IMO-AG-30自动定理证明任务上创下了新的最优纪录,解决了30道题中的27道,成为首个性能超越IMO金牌选手的AI方法。

英文摘要:

Proving geometric theorems constitutes a hallmark of visual reasoning combining both intuitive and logical skills. Therefore, automated theorem proving of Olympiad-level geometry problems is considered a notable milestone in human-level automated reasoning. The introduction of AlphaGeometry, a neuro-symbolic model trained with 100 million synthetic samples, marked a major breakthrough. It solved 25 of 30 International Mathematical Olympiad (IMO) problems whereas the reported baseline based on Wu's method solved only ten. In this note, we revisit the IMO-AG-30 Challenge introduced with AlphaGeometry, and find that Wu's method is surprisingly strong. Wu's method alone can solve 15 problems, and some of them are not solved by any of the other methods. This leads to two key findings: (i) Combining Wu's method with the classic synthetic methods of deductive databases and angle, ratio, and distance chasing solves 21 out of 30 methods by just using a CPU-only laptop with a time limit of 5 minutes per problem. Essentially, this classic method solves just 4 problems less than AlphaGeometry and establishes the first fully symbolic baseline strong enough to rival the performance of an IMO silver medalist. (ii) Wu's method even solves 2 of the 5 problems that AlphaGeometry failed to solve. Thus, by combining AlphaGeometry with Wu's method we set a new state-of-the-art for automated theorem proving on IMO-AG-30, solving 27 out of 30 problems, the first AI method which outperforms an IMO gold medalist.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑