DeepMind用神经符号方法严谨解决数学难题，做AI推理或形式验证的开发者值得关注——这比纯LLM方案更可靠，也暗示了未来研究的方向。
DeepMind团队使用神经符号方法（neurosymbolic）成功解决了9个开放的Erdos问题，工作比OpenAI更细致、定量化。该方法结合了LLM和Lean证明助手，实现自主推理，仅在形式验证通过后才进行人工审核。Gary Marcus评论称，OpenAI可能因知道DeepMind即将发布而仓促推出自己的方案。这一进展展示了神经符号方法在数学推理中的潜力，也引发了关于研究竞争和严谨性的讨论。
neurosymbolic by @swarat et al for the Erdos win, with much more careful, quantitative work than ope...
neurosymbolic by @swarat et al for the Erdos win, with much more careful, quantitative work than openai’s in hindsight i wonder whether OpenAI rushed theirs out, knowing this was coming? Przemek Chojecki | PC @prz_chojecki Another 9 open Erdos problems solved, this time by DeepMind team. Interesting loop of LLM - Lean agents working autonomously, and only after it's verified formally, going through human review. 🔗 View Quoted Tweet 💬 4 🔄 0 ❤️ 8 👀 1043 📊 4 ⚡