Sakana AI 在 OpenMath 2026 数学黑客松企业组夺冠

摘要

Sakana AI 在哈佛创新实验室与 Stephen Wolfram 合办的“Recursive Self Improvement in Mathematics”Hack（OpenMath 2026）中获企业组第一名。团队主要依托 Sakana Fugu 模型和内部智能体工具，贡献了 14 个数学族，其中 6 个为完整解决，另含新界与结构性进展。团队表示将在后续报告中分享方法与经验。

摘要由模型根据原文撰写，以原文为准。

Sakana AI won 1st place in the company category at the “Recursive Self Improvement in Mathematics” Hack (OpenMath 2026), held with @stephen_wolfram at Harvard Innovation Labs.

Competition: https://rsihouse.ai/openmath
Results: https://bit.ly/4yT2Dav

Drawing mainly on our Sakana Fugu models and internal agentic tools, our team (Rachel Teo, Abderrahmene Hamdi, Wenyi Wang) contributed 14 mathematical families, including 6 complete resolutions, plus new bounds and structural advances.

Thanks to the organizers and everyone involved.
We plan to share more about our approach and learnings in a future report.

SakanaAILabs. Sakana AI won 1st place in the company category at the “Recursive Self Improvement in Mathematics” Hack (OpenMath 2026), held with @steph...[EB/OL]. (2026-10-29)[访问日期]. https://x.com/SakanaAILabs/status/2115813405835846058.

Sakana AI 在 OpenMath 2026 数学黑客松企业组夺冠

摘要

正文 · 原文

引用原文