PulseAugur
中
实时 00:27:39
English(EN) Kimina-Prover: Applying Test-time RL Search on Large Formal Reasoning Models

Hugging Face发布Kimina-Prover-72B,采用新颖的强化学习搜索进行形式推理

Hugging Face发布了Kimina-Prover-72B,这是一款基于Qwen2.5-72B的新型最先进定理证明模型,并使用Kimi k1.5强化学习管道进行训练。该模型引入了一个测试时强化学习搜索框架,使其能够递归地发现和组合引理以进行复杂证明,并具备一种错误修复能力,可以解释Lean错误消息并提出修正。在miniF2F基准测试中,Kimina-Prover的通过率为92.2%,超过了以往的方法。 AI

影响 为形式推理基准设定了新的最先进水平,有可能加速人工智能在数学和科学发现中的作用。

排序理由 主要AI实验室(Hugging Face)发布新模型,具备新颖功能和基准测试结果。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

在 Hugging Face Blog 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →

Hugging Face发布Kimina-Prover-72B,采用新颖的强化学习搜索进行形式推理

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
Significant
主要AI实验室(Hugging Face)发布新模型,具备新颖功能和基准测试结果。[lever_c_demoted from frontier_release: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
model release, paper, 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
491 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

  1. Hugging Face Blog TIER_1 English(EN) ·

    Kimina-Prover:将测试时强化学习搜索应用于大型形式推理模型