按年被提到
20252025 · 2 次2026
数学、逻辑与理论›AI 数学与定理证明·arXiv:2502.03544 · cs.AI

Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2

Yuri Chervonyi, Trieu H. Trinh, Miroslav Olšák, Xiaomeng Yang, Hoang Nguyen, Marcelo Menegali, Junehyuk Jung, Junsu Kim, Vikas Verma, Quoc V. Le, Thang Luong · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-02-07 · 最近 2025-05-13
2不同的人
2活跃月份
2讨论串
29被引(OpenAlex)
arXiv 摘要(候选层不写导读)

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.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论falcor84 · 2025-05

“There are a ton of big examples of advances across all subfields of AI over the last year, but the first one that came to my mind was AlphaGeometry2 [0], which combines Gemini with a symbolic agent to solve (offer proofs for) the vast majority of IMO geometry problems. I believe that this sort of approach can be applied to many other types of problems. […”

A conversation about AI for science with Jason Pruet原评论 ↗
被提交为 story · 1 次