English(EN) SkillEvoLean: Mutation-enhanced skill evolution for Lean provers

新AI框架通过增强式突变技能进化提升定理证明能力

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-03 04:00

研究人员开发了SkillEvoLean，一个用于增强大型语言模型在形式化定理证明中能力的框架。该方法采用增强式突变技能进化，它同时更新高级求解策略和参考知识。当标准方法未能找到成功路径时，SkillEvoLean使用突变来采样数学概念并生成新的技能候选。在MiniF2F和PutnamBench等基准测试以及IMO 2025和USAMO 2026问题上使用GPT-5.5进行测试，SkillEvoLean相比基线方法实现了显著更高的证明成功率。 AI

影响增强了AI在形式化定理证明中的能力，可能加速数学发现和形式化验证。

排序理由该条目是一篇研究论文，详细介绍了一种用于AI代理在形式化定理证明中的新方法。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

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

本文如何被排名

Signal score: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该条目是一篇研究论文，详细介绍了一种用于AI代理在形式化定理证明中的新方法。[lever_c_demoted from research: 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: paper, model release; 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: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Kuo Zhou, ZiXion Yang, Lu Zhang · 2026-10-03 04:00

SkillEvoLean：增强突变技能以改进Lean证明器

arXiv:2610.01799v1 Announce Type: new Abstract: Skill evolution offers a promising way to improve large language model agents without updating their parameters, but its use in formal theorem proving remains underexplored. Existing methods mainly target natural-language reasoning,…

本文如何被排名

报道来源 [1]

SkillEvoLean：增强突变技能以改进Lean证明器

相关实体

相关话题