PulseAugur
中
实时 00:52:05
English(EN) MA-ProofBench: A Two-Tiered Evaluation of LLMs for Theorem Proving in Mathematical Analysis

新的大语言模型（LLM）框架和基准推动形式数学推理发展

作者 PulseAugur 编辑部 · [9 个来源] ·

研究人员正在开发新的方法和基准来提高大语言模型（LLM）的形式数学推理能力。一种名为 Diffusion-Proof 的方法利用扩散大语言模型（dLLMs）进行定理证明，在 ProofNet-Test 和 MiniF2F-Test 等基准测试中表现优于自回归模型，甚至解决了领先模型无法解决的国际数学奥林匹克问题。另一项开发 Visored 提供了一个旨在通过模仿自然语言和自动化常规步骤来处理大语言模型生成数学的证明器。此外，Mask-Proof 引入了一个用于从真实证明中创建自动可检查的掩码步骤任务的流水线，以评估大语言模型（LLM）的步骤级推理能力，而 MA-ProofBench 提供了一个专门针对数学分析的新基准，突显了当前大语言模型（LLM）在该复杂领域中的局限性。 AI

影响 这些进展旨在提高大语言模型（LLM）在复杂数学推理方面的能力，可能对科学发现和形式验证产生影响。

排序理由 多篇研究论文介绍了用于大语言模型（LLM）数学推理的新方法和基准。

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 9 个来源。 我们如何撰写摘要 →

新的大语言模型（LLM）框架和基准推动形式数学推理发展

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Research
多篇研究论文介绍了用于大语言模型（LLM）数学推理的新方法和基准。
Source corroboration
9 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
paper, model release, product
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
120 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+3 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [9]

  1. arXiv cs.AI TIER_1 English(EN) · Manish Acharya, Zhenyu Liao, Yueke Zhang, Kevin Leach, Yu Huang, Yifan Zhang ·

    VERITAS: 验证器引导的零样本形式定理证明搜索

    arXiv:2606.19399v1 Announce Type: cross Abstract: LLM-based formal provers often collapse rich verifier signals (syntax errors, type mismatches, partial goal progress) into a binary pass/fail bit. We present VERITAS, a zero-shot framework that routes every verifier signal back in…

  2. arXiv cs.LG TIER_1 English(EN) · Slim Barkallah, Luke Bailey, Kaiyue Wen, Mohammed Abouzaid, Tengyu Ma ·

    自动证明验证的伪形式化

    arXiv:2605.20531v2 Announce Type: replace-cross Abstract: Reliable verification of proofs remains a bottleneck for training and evaluating AI systems on hard mathematical reasoning. Fully formal proofs, in languages like Lean, are easy to verify because they are unambiguous and m…

  3. arXiv cs.LG TIER_1 English(EN) · Ruida Wang, Rui Pan, Pengcheng Wang, Shizhe Diao, Tong Zhang ·

    Diffusion-Proof：超越自回归生成形式化定理证明的配方

    arXiv:2606.19315v1 Announce Type: new Abstract: Enhancing the formal math reasoning capabilities of Large Language Models (LLMs) has become a key focus in both mathematical and computer science communities in recent years. While significant progress has been made in using state-o…

  4. arXiv cs.LG TIER_1 English(EN) · Tong Zhang ·

    Diffusion-Proof：超越自回归生成的形式定理证明配方

    Enhancing the formal math reasoning capabilities of Large Language Models (LLMs) has become a key focus in both mathematical and computer science communities in recent years. While significant progress has been made in using state-of-the-art Auto-Regressive (AR) LLMs for formal t…

  5. Hugging Face Daily Papers TIER_1 English(EN) ·

    Diffusion-Proof：超越自回归生成形式化定理证明的配方

    Enhancing the formal math reasoning capabilities of Large Language Models (LLMs) has become a key focus in both mathematical and computer science communities in recent years. While significant progress has been made in using state-of-the-art Auto-Regressive (AR) LLMs for formal t…

  6. arXiv cs.AI TIER_1 English(EN) · Xiyu Zhai, Xinyi Chen, Yiping Wang, Runlong Zhou, Liao Zhang, Simon S. Du ·

    Visored：用于 LLM 生成数学的受控自然语言证明器

    arXiv:2606.17581v1 Announce Type: cross Abstract: We present a dependent-type-based prover designed around the way LLMs (and humans) tend to write mathematics, complementing existing systems such as Lean and Rocq. Its core design choices are a surface that imitates mathematical n…

  7. arXiv cs.AI TIER_1 English(EN) · Chuxue Cao, Mengze Li, Juntao Dai, Jinluan Yang, Zijian Zhao, Shengyu Zhang, Weijie Shi, Chengzhong Liu, Sirui Han, Yike Guo ·

    通过一阶逻辑定理证明实现大语言模型的高级数学推理

    arXiv:2506.17104v2 Announce Type: replace Abstract: Large language models (LLMs) have shown promising first-order logic (FOL) reasoning capabilities with applications in various areas. However, their effectiveness in complex mathematical reasoning involving multi-step FOL deducti…

  8. arXiv cs.AI TIER_1 English(EN) · Jierui Zhang, Siyuan Tan, Xinhang Li, Longzhuangzhi Lin, Dailin Li, Chengfeng Gu, Xinping Li, Yaxian Hao, Shengjia Liang, Yuxiang Ren, Wenhao Liu ·

    Mask-Proof：一个基于LLM的数学证明自动化数据策管线

    arXiv:2606.15258v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly capable of mathematical problem solving and can even assist with research-level proofs, yet we still lack a scalable and reproducible way to measure step-level reasoning in long proofs a…

  9. arXiv cs.AI TIER_1 English(EN) · Lushi Pu, Weiming Zhang, Xinheng Xie, Zixuan Fu, Bingxiang He, Hongya Lyu, Xin Li, Jie Zhou, Yudong Wang ·

    MA-ProofBench：数学分析中用于定理证明的大型语言模型的两级评估

    arXiv:2606.13782v1 Announce Type: new Abstract: Large Language Models (LLMs) have made notable progress in automated theorem proving, yet existing formal benchmarks remain limited in both mathematical coverage and difficulty. Most are concentrated in areas that are easier to form…

相关实体

相关话题