#mathematical proofs

82 stories · 4 in 7 days · 24 in 30 days
Stories, products and papers tagged "mathematical proofs", newest first.
Nov 13
Chinese contentarXiv 研究:LLM 数学证明风格与人类不同,偏爱从头构建推理链

研究者让三个大模型重证了 Euclid《Elements》全部 465 个命题,再用网络分析对比引用结构。发现 AI 有 40% 引用指向定义和公设,人类只有 13%,AI 喜欢从零搭论证而不是引用成熟定理。做形式化验证或用模型辅助写数学论文的人都值得看看这套量化方法。

arXiv cs.AI@Xiaokai Li et al. (6)Source
Nov 12
IndustryBuildersMulti-source16:36
Chinese contentAnthropic Lance Martin:1000 个 Claude 智能体协作形式化费马大定理

Anthropic 的人现场讲了一个真实案例:1000 个 Claude 智能体一起做费马大定理的形式化。最有信息量的是他的判断——长时程智能体拼的是奖励和评测,不是提示词,做智能体的开发者应该会想对照下自己的设计思路。

Event
AI Will@FinanceYF5Source
Nov 7
Nov 6
Oct 30
Oct 28
Oct 27
Oct 23
Oct 22
Oct 20
Oct 19
Oct 18
Oct 17
Oct 16
ModelsBuildersSelected11:09
Intern-S2 Helps Resolve Ghys's Conjecture in Complex Dimension Three

A 30-year-old conjecture falling to a Chinese lab's model plus Lean verification shows AI moving from coding benchmarks into formal mathematics, where every step is machine-checked. Researchers in theorem proving and anyone tracking Chinese labs' frontier ambitions should follow the write-up. It also gives Lean-based formalisation workflows a high-profile proof point against informal LLM math claims.

InternLM 书生@intern_lmSource
Oct 13
Oct 10
Oct 9
Oct 8
Oct 7
PapersUS vs ChinaMulti-sourceSelected72°08:40
OpenAI releases new mathematical results from internal frontier model

The release shows a frontier lab outsourcing disclosure decisions to an external academic advisory body, a model other labs may copy for sensitive research claims. Mathematicians and AI researchers can review the actual proofs and methods on the public GitHub repository. The Institute for Advanced Study involvement gives the results an academic credibility check that benchmark leaderboards lack.

Event
Thomas Wolf@Thom_WolfSource