PulseAugur
实时 23:35:15
English(EN) Proof-Refactor: Refactoring Generated Formal Proofs into Modular Artifacts

AI框架通过新技术提升形式化定理证明能力

研究人员开发了新的框架,利用大型语言模型增强形式化定理证明能力。Goedel-Architect 采用蓝图生成和精炼策略,使用 DeepSeek-V4-Flash 模型在 MiniF2F-testPutnamBench 等基准测试中取得了最先进的性能。Proof-Refactor 专注于提高 LLM 生成证明的模块化、可读性和可维护性,在 PutnamBench 数据集上表现优于现有基线。另一种方法 Compile to Compress 利用编译器输出来高效地精炼证明尝试,使用较小的模型在 PutnamBench 上取得了顶级结果。 AI

影响 AI驱动的形式化定理证明的这些进展可能会加速数学发现和软件验证。

排序理由 多篇研究论文介绍了使用AI进行形式化定理证明的新颖框架和技术。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 6 个来源。 我们如何撰写摘要 →

AI框架通过新技术提升形式化定理证明能力

报道来源 [6]

  1. arXiv cs.AI TIER_1 English(EN) · Jui-Hui Chung, Ziyang Cai, Zihao Li, Qishuo Yin, Rohit Agarwal, Simon Park, Rodrigo Porto, Narutatsu Ri, Ziran Yang, Shange Tang, Xingyu Dang, Hongzhou Lin, Mengdi Wang, Danqi Chen, Chi Jin, Liam H Fowl, Sanjeev Arora ·

    Goedel-Architect:通过蓝图生成和精炼简化形式定理证明

    arXiv:2606.06468v1 Announce Type: new Abstract: We introduce Goedel-Architect, an agentic framework for formal theorem proving in Lean 4 centered on blueprint generation and refinement. A blueprint is a dependency graph of definitions and lemmas that builds up to the main theorem…

  2. arXiv cs.AI TIER_1 English(EN) · Sanjeev Arora ·

    Goedel-Architect:通过蓝图生成和精炼简化形式定理证明

    We introduce Goedel-Architect, an agentic framework for formal theorem proving in Lean 4 centered on blueprint generation and refinement. A blueprint is a dependency graph of definitions and lemmas that builds up to the main theorem. First, Goedel-Architect generates a blueprint …

  3. arXiv cs.AI TIER_1 English(EN) · Yiming Fu, Peixuan Liu, Zichen Wang, Kun yuan ·

    Proof-Refactor:将生成的形式化证明重构为模块化构件

    arXiv:2606.03743v1 Announce Type: new Abstract: While Large Language Models (LLMs) have shown strong performance in generating formal proofs, their outputs often remain less readable, modular, maintainable, and reusable than proofs in mature formal mathematics libraries. We argue…

  4. arXiv cs.AI TIER_1 English(EN) · Kun yuan ·

    Proof-Refactor:将生成的形式化证明重构为模块化构件

    While Large Language Models (LLMs) have shown strong performance in generating formal proofs, their outputs often remain less readable, modular, maintainable, and reusable than proofs in mature formal mathematics libraries. We argue that this gap stems in part from the compile-fi…

  5. arXiv cs.AI TIER_1 English(EN) · Guchan Li, Rui Tian, Hongning Wang ·

    编译到压缩:通过编译器输出来增强形式定理证明器

    arXiv:2604.18587v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated significant potential in formal theorem proving, yet state-of-the-art performance often necessitates prohibitive test-time compute via massive roll-outs or extended context wi…

  6. Pandaily TIER_1 English(EN) · [email protected] (Pandaily) ·

    DeepSeek V4 赋能 Goedel-Architect:形式定理证明成本降低 500 倍

    A research team from Princeton University's Language and Intelligence Lab (PLI) has published a groundbreaking paper on Goedel-Architect, an agent framework for formal theorem proving that achieves state-of-the-art results at a fraction of the cost of existing systems.