arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.03544cs.AIcs.LG
收藏

在解决奥数几何问题上超越金牌得主的AlphaGeometry2

Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2

Google DeepMind(谷歌DeepMind);University of Cambridge(剑桥大学);Georgia Institute of Technology(佐治亚理工学院);Brown University(布朗大学);Seoul National University(首尔国立大学)

Yuri Chervonyi, Trieu H. Trinh, Miroslav Olšák, Xiaomeng Yang, Hoang Nguyen, Marcelo Menegali, Junehyuk Jung, Junsu Kim, Vikas Verma, Quoc V. Le, Thang Luong

AI总结:

AlphaGeometry2通过改进的语言模型和知识共享机制,显著提升了解决几何问题的能力,达到超越金牌得主的水平,并推动了自动系统在几何问题解决中的应用。

摘要:

我们介绍了AlphaGeometry2(AG2),这是在(Trinh等人,2024)中引入的AlphaGeometry的显著改进版本,现已在解决奥数几何问题上超越了平均金牌得主。为此,我们首先扩展了原始AlphaGeometry语言,以解决涉及物体运动的问题,以及包含角度线性方程、比例和距离的问题。这,加上对非构造性问题的支持,使AlphaGeometry语言在国际数学奥林匹克竞赛(IMO)2000-2024几何问题上的覆盖率达到从66%提高到88%。通过使用Gemini架构进行更好的语言建模,以及一种新的知识共享机制,使搜索过程在搜索树之间实现有效的沟通,AG2的搜索过程也得到了显著改进。此外,对符号引擎和合成数据生成的进一步改进,使AG在解决过去25年所有几何问题的总体解决率从54%提高到84%。AG2也是在IMO 2024中达到银牌标准的系统的一部分https://deepmind.google/blog/ai-solves-imo-problems-at-silver-medal-level/。最后,我们报告了在使用AG2作为完全自动化系统的一部分,以可靠地解决自然语言输入的几何问题方面的进展。代码:https://github.com/google-deepmind/alphageometry2。

英文摘要:

We present AlphaGeometry2 (AG2), a significantly improved version of AlphaGeometry introduced in (Trinh et al., 2024), which has now surpassed an average gold medalist in solving Olympiad geometry problems. To achieve this, we first extend the original AlphaGeometry language to tackle problems involving movements of objects, and problems containing linear equations of angles, ratios, and distances. This, together with support for non-constructive problems, has markedly improved the coverage rate of the AlphaGeometry language on International Math Olympiads (IMO) 2000-2024 geometry problems from 66% to 88%. The search process of AG2 has also been greatly improved through the use of Gemini architecture for better language modeling, and a novel knowledge-sharing mechanism that enables effective communication between search trees. Together with further enhancements to the symbolic engine and synthetic data generation, we have significantly boosted the overall solving rate of AG to 84% on all geometry problems over the last 25 years, compared to 54% previously. AG2 was also part of the system that achieved the silver-medal standard at IMO 2024 https://deepmind.google/blog/ai-solves-imo-problems-at-silver-medal-level/. Finally, we report progress towards using AG2 as a part of a fully automated system that reliably solves geometry problems from natural language input. Code: https://github.com/google-deepmind/alphageometry2.

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。

↑