Banger paper from Google DeepMind on open-ended math discovery with agents. This is one of the earl...
TL;DR · AI 摘要
Google DeepMind利用Gemini代理在数学发现领域取得突破，自主发现并验证了Busy Beaver问题中Turing机器的加速规则。
核心要点
- Gemini代理通过Lean证明验证，确保数学发现的正确性
- 发现11台未解决Turing机器的加速规则，命名为Cryptids
- Busy Beaver问题的不可计算性要求代理自主选择研究对象
结构提纲
按章节快速跳转。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- AI自主数学发现
- 核心机制
- Gemini代理选择研究对象
- 模式识别生成加速规则
- 验证体系
- Lean形式化证明
- 结果可信度保障
- 研究对象
- Busy Beaver问题
- Cryptids机器
金句 / Highlights
值得收藏与分享的关键句。
Gemini-based agent发现了十一台未解决的Turing机器的加速规则
通过Lean证明验证，确保结果不依赖模型推理可信度
Cryptids的运行轨迹具有精确描述但停机问题仍待解决
elvis on X: "Banger paper from Google DeepMind on open-ended math discovery with agents. This is one of the early, exciting works I have seen on autonomous AI-powered discoveries. (bookmark it) A Gemini-based agent found and formally verified new acceleration rules for eleven unresolved Turing m… / X
elvis
@omarsar0
Banger paper from Google DeepMind on open-ended math discovery with agents. This is one of the early, exciting works I have seen on autonomous AI-powered discoveries. (bookmark it) A Gemini-based agent found and formally verified new acceleration rules for eleven unresolved Turing machines in BB(6), the current frontier of the Busy Beaver problem. Busy Beaver is uncomputable, so no fixed list of problems exists. The agent has to pick machines, spot patterns in their execution traces, and propose compact rules that summarize many steps at once. Each proposed rule then goes through informal reasoning and a Lean proof. Only proved rules are kept, so the result does not depend on trusting the model's reasoning. The authors provisionally call these machines Cryptids. Their runs from a blank tape now have exact, compact descriptions, but whether they halt is still open. This is a good example of an agent producing new, formally checked mathematical results on problems it chose itself.
arxiv.org/abs/2610.22603
Chat with Paper:
academy.dair.ai/papers/at-the-…
4:55 PM · Oct 19, 2026
·
4,784
Views
24
7
57
38