OK! My Google colleague Thang Luong shared some exciting updates about AlphaGeometry2!
AG2 now has surpassed the average gold-medalist in solving Olympiad geometry problems, w/ a solve rate of 84% compared to 54% previously!
Paper: arxiv.org/abs/2502.03544
See full list of authors on link
AG2 now has surpassed the average gold-medalist in solving Olympiad geometry problems, w/ a solve rate of 84% compared to 54% previously!
Paper: arxiv.org/abs/2502.03544
See full list of authors on link
February 8, 2025 at 7:42 PM
OK! My Google colleague Thang Luong shared some exciting updates about AlphaGeometry2!
AG2 now has surpassed the average gold-medalist in solving Olympiad geometry problems, w/ a solve rate of 84% compared to 54% previously!
Paper: arxiv.org/abs/2502.03544
See full list of authors on link
AG2 now has surpassed the average gold-medalist in solving Olympiad geometry problems, w/ a solve rate of 84% compared to 54% previously!
Paper: arxiv.org/abs/2502.03544
See full list of authors on link
The company’s AlphaGeometry2 now reaches level of gold-medal students in the International Mathematical Olympiad
go.nature.com/4jSPnfJ
go.nature.com/4jSPnfJ
DeepMind AI crushes tough maths problems on par with top human solvers
The company’s AlphaGeometry2 is now competitive reaches level of gold-medal students in the International Mathematical Olympiad.
go.nature.com
February 7, 2025 at 5:14 PM
The company’s AlphaGeometry2 now reaches level of gold-medal students in the International Mathematical Olympiad
go.nature.com/4jSPnfJ
go.nature.com/4jSPnfJ
Hey @jeffdean.bsky.social , help bring posts like the AlphaGeometry2 one to this network please!
Using the other place as the only place is bad for the field!
Using the other place as the only place is bad for the field!
February 8, 2025 at 7:25 PM
Hey @jeffdean.bsky.social , help bring posts like the AlphaGeometry2 one to this network please!
Using the other place as the only place is bad for the field!
Using the other place as the only place is bad for the field!
DeepMind says its AlphaGeometry2 model solved 84% of International Math Olympiad's geometry problems from the last 25 years, surpassing average gold medalists (Kyle Wiggers/TechCrunch)
Main Link | Techmeme Permalink
Main Link | Techmeme Permalink
February 7, 2025 at 7:45 PM
DeepMind says its AlphaGeometry2 model solved 84% of International Math Olympiad's geometry problems from the last 25 years, surpassing average gold medalists (Kyle Wiggers/TechCrunch)
Main Link | Techmeme Permalink
Main Link | Techmeme Permalink
DeepMind claims its AI performs better than International Mathematical Olympiad gold medalists
DeepMind claims its AI performs better than International Mathematical Olympiad gold medalists
An AI system developed by Google DeepMind, Google’s leading AI research lab, appears to have surpassed the average gold medalist in solving geometry problems in an international mathematics competition. The system, called AlphaGeometry2, is an improved…
tcrn.ch
February 7, 2025 at 6:59 PM
DeepMind claims its AI performs better than International Mathematical Olympiad gold medalists
Davis and Marcus dive deep in AlphaGeometry 2, deflating hype but also pointing to some genuine positives.
garymarcus.substack.com/p/alphageome...
garymarcus.substack.com/p/alphageome...
AlphaGeometry2: Impressive accomplishment, but still a long path ahead
What GoogleDeepMind’s latest does and doesn’t show, and what we like about it
garymarcus.substack.com
February 17, 2025 at 5:27 PM
Davis and Marcus dive deep in AlphaGeometry 2, deflating hype but also pointing to some genuine positives.
garymarcus.substack.com/p/alphageome...
garymarcus.substack.com/p/alphageome...
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
AlphaGeometry2 (AG2) surpasses IMO gold medalists in solving Olympiad geometry problems by expanding its problem domain, enhancing symbolic reasoning, and integrating a stronger language model.
AlphaGeometry2 (AG2) surpasses IMO gold medalists in solving Olympiad geometry problems by expanding its problem domain, enhancing symbolic reasoning, and integrating a stronger language model.
February 9, 2025 at 8:07 PM
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
AlphaGeometry2 (AG2) surpasses IMO gold medalists in solving Olympiad geometry problems by expanding its problem domain, enhancing symbolic reasoning, and integrating a stronger language model.
AlphaGeometry2 (AG2) surpasses IMO gold medalists in solving Olympiad geometry problems by expanding its problem domain, enhancing symbolic reasoning, and integrating a stronger language model.
These kinds of neurosymbolic systems – combining symbolic DSLs, search trees, and LLMs – are some of the more interesting things currently going on in AI imo.
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
We present AlphaGeometry2, 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. ...
arxiv.org
February 7, 2025 at 8:05 PM
These kinds of neurosymbolic systems – combining symbolic DSLs, search trees, and LLMs – are some of the more interesting things currently going on in AI imo.
Top Trending Papers on alphaXiv this week!📈
🚀This week, AI is leveling up—from solving Olympiad geometry with AlphaGeometry2 to generating motion with VideoJAM, while also mastering the art of reasoning and adversarial resilience with tools like DeepRAG and LIMO. 🚨
🚀This week, AI is leveling up—from solving Olympiad geometry with AlphaGeometry2 to generating motion with VideoJAM, while also mastering the art of reasoning and adversarial resilience with tools like DeepRAG and LIMO. 🚨
February 9, 2025 at 8:07 PM
Top Trending Papers on alphaXiv this week!📈
🚀This week, AI is leveling up—from solving Olympiad geometry with AlphaGeometry2 to generating motion with VideoJAM, while also mastering the art of reasoning and adversarial resilience with tools like DeepRAG and LIMO. 🚨
🚀This week, AI is leveling up—from solving Olympiad geometry with AlphaGeometry2 to generating motion with VideoJAM, while also mastering the art of reasoning and adversarial resilience with tools like DeepRAG and LIMO. 🚨
GoogleのAI、国際数学オリンピックで「金メダル」を達成。人間には思いつかないエレガントな解法を出力（生成AIクローズアップ） @TechnoEdgeJP www.techno-edge.net/article/2025...
GoogleのAI、国際数学オリンピックで「金メダル」を達成。人間には思いつかないエレガントな解法を出力（生成AIクローズアップ） | テクノエッジ TechnoEdge
国際数学オリンピックで金メダル相当のパフォーマンスを達成したモデルを提示する論文「Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2」に注目します。
www.techno-edge.net
February 21, 2025 at 1:23 AM
GoogleのAI、国際数学オリンピックで「金メダル」を達成。人間には思いつかないエレガントな解法を出力（生成AIクローズアップ） @TechnoEdgeJP www.techno-edge.net/article/2025...
Gold-medalist performance in solving olympiad geometry with AlphaGeometry2. ~ Yuri Chervonyi et als. arxiv.org/abs/2502.03544 #AI #AlphaGeometry #Math
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
We present AlphaGeometry2, 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. ...
arxiv.org
March 4, 2025 at 9:46 AM
Gold-medalist performance in solving olympiad geometry with AlphaGeometry2. ~ Yuri Chervonyi et als. arxiv.org/abs/2502.03544 #AI #AlphaGeometry #Math
- s1: Simple test-time scaling
- OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
- Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
- DeepRAG: Thinking to Retrieval Step by Step for Large Language Models
- OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
- Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
- DeepRAG: Thinking to Retrieval Step by Step for Large Language Models
February 9, 2025 at 8:07 PM
- s1: Simple test-time scaling
- OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
- Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
- DeepRAG: Thinking to Retrieval Step by Step for Large Language Models
- OmniHuman-1: Rethinking the Scaling-Up of One-Stage Conditioned Human Animation Models
- Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
- DeepRAG: Thinking to Retrieval Step by Step for Large Language Models
AlphaGeometry2 can solve 84% of IMO geometry problems.
But the interesting part isn't the model — it's the architecture.
LLM + symbolic reasoning + search.
Here’s a deep dive into how the system works:
luhuidev.medium.com/alphageometr...
But the interesting part isn't the model — it's the architecture.
LLM + symbolic reasoning + search.
Here’s a deep dive into how the system works:
luhuidev.medium.com/alphageometr...
AlphaGeometry2 Deep Dive: How Does Google AI Solve IMO Geometry Problems?
## Introduction
luhuidev.medium.com
March 6, 2026 at 12:43 PM
AlphaGeometry2 can solve 84% of IMO geometry problems.
But the interesting part isn't the model — it's the architecture.
LLM + symbolic reasoning + search.
Here’s a deep dive into how the system works:
luhuidev.medium.com/alphageometr...
But the interesting part isn't the model — it's the architecture.
LLM + symbolic reasoning + search.
Here’s a deep dive into how the system works:
luhuidev.medium.com/alphageometr...
😮 Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
We present AlphaGeometry2, 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.…
buff.ly
February 8, 2025 at 10:11 PM
😮 Gold-medalist Performance in Solving Olympiad Geometry with AlphaGeometry2
DeepMind's AlphaGeometry2 AI demonstrates gold-medal level performance by solving 42 out of 50 International Mathematical Olympiad problems, surpassing the average human gold medalist. doi.org/g84k4b
DeepMind AI achieves gold-medal level performance on challenging Olympiad math questions
A team of researchers at Google's DeepMind project, reports that its AlphaGeometry2 AI performed at a gold-medal level when tasked with solving problems that were given to high school students participating in the International Mathematical Olympiad (IMO) over the past 25 years.
techxplore.com
February 10, 2025 at 4:32 PM
DeepMind's AlphaGeometry2 AI demonstrates gold-medal level performance by solving 42 out of 50 International Mathematical Olympiad problems, surpassing the average human gold medalist. doi.org/g84k4b
Google Deepmind 的 AlphaGeometry2
1. 第一次达到了 IMO 金牌选手的平均水平
2. 50道 2000年 到 2024年的 IMO 几何题目，OpenAI o1 一道都解决不了，而 AG2 可以解决 42 道，AG1 的水平是 27 道
3. “... many AlphaGeometry solutions to exhibit superhuman creativity”
arxiv.org/pdf/2502.03544
1. 第一次达到了 IMO 金牌选手的平均水平
2. 50道 2000年 到 2024年的 IMO 几何题目，OpenAI o1 一道都解决不了，而 AG2 可以解决 42 道，AG1 的水平是 27 道
3. “... many AlphaGeometry solutions to exhibit superhuman creativity”
arxiv.org/pdf/2502.03544
arxiv.org
February 8, 2025 at 2:50 AM
Google Deepmind 的 AlphaGeometry2
1. 第一次达到了 IMO 金牌选手的平均水平
2. 50道 2000年 到 2024年的 IMO 几何题目，OpenAI o1 一道都解决不了，而 AG2 可以解决 42 道，AG1 的水平是 27 道
3. “... many AlphaGeometry solutions to exhibit superhuman creativity”
arxiv.org/pdf/2502.03544
1. 第一次达到了 IMO 金牌选手的平均水平
2. 50道 2000年 到 2024年的 IMO 几何题目，OpenAI o1 一道都解决不了，而 AG2 可以解决 42 道，AG1 的水平是 27 道
3. “... many AlphaGeometry solutions to exhibit superhuman creativity”
arxiv.org/pdf/2502.03544
Google DeepMind’s AlphaGeometry2 AI Achieves Gold-Medal Math Olympiad Performance
Google DeepMind's AlphaGeometry2 (AG2) AI model solved 84% of the geometry problems from the last 25 years of International Math Olympiads (IMO), outperforming the average human gold-medalist per…
#ai #deepmind #news
Google DeepMind's AlphaGeometry2 (AG2) AI model solved 84% of the geometry problems from the last 25 years of International Math Olympiads (IMO), outperforming the average human gold-medalist per…
#ai #deepmind #news
Google DeepMind’s AlphaGeometry2 AI Achieves Gold-Medal Math Olympiad Performance
Google DeepMind's AlphaGeometry2 (AG2) AI model solved 84% of the geometry problems from the last 25 years of International Math Olympiads (IMO), outperforming the average human gold-medalist performance. By Anthony Alford
www.infoq.com
February 26, 2025 at 10:40 AM
ШІ від DeepMind перевершує золотих медалістів Міжнародної математичної олімпіади channeltech.space/ai/deepmind-...
AlphaGeometry2 від DeepMind перевершує золотих медалістів Міжнародної математичної олімпіади - Channel Tech
Google DeepMind представила оновлену версію свого ШІ — AlphaGeometry2, який показав вражаючі результати у розв'язанні геометричних задач.
channeltech.space
February 9, 2025 at 1:25 PM
ШІ від DeepMind перевершує золотих медалістів Міжнародної математичної олімпіади channeltech.space/ai/deepmind-...
This is a good look at what might be around the corner for math with AlphaGeometry2. #EduSky #AIEdu
www.scientificamerican.com/article/goog...
www.scientificamerican.com/article/goog...
February 11, 2025 at 3:26 PM
This is a good look at what might be around the corner for math with AlphaGeometry2. #EduSky #AIEdu
www.scientificamerican.com/article/goog...
www.scientificamerican.com/article/goog...
🔗 AlphaGeometry2: Deepmind AI outperforms math Olympians at geometry tasks
#NeuroSymbolic #AI #FutureOfAI
#InspiredbyNature
the-decoder.com/alphageometr...
#NeuroSymbolic #AI #FutureOfAI
#InspiredbyNature
the-decoder.com/alphageometr...
AlphaGeometry2: Deepmind AI outperforms math Olympians at geometry tasks
The latest version of Deepmind's AlphaGeometry system can solve geometry problems better than most human experts, matching the performance of top math competition winners.
the-decoder.com
February 10, 2025 at 5:30 PM
🔗 AlphaGeometry2: Deepmind AI outperforms math Olympians at geometry tasks
#NeuroSymbolic #AI #FutureOfAI
#InspiredbyNature
the-decoder.com/alphageometr...
#NeuroSymbolic #AI #FutureOfAI
#InspiredbyNature
the-decoder.com/alphageometr...