用大模型自动合成程序不变式，把验证速度拉满，搞形式化验证的必读新作。
arXiv:2509.21629v4 Announce Type: replace-cross Abstract: Program verification relies on loop invariants, yet automatically discovering strong invaria…
用LLM代理自动优化约束编程模型，突破传统人工调参瓶颈，让求解器性能跃升。
arXiv:2608.08127v1 Announce Type: new Abstract: The runtime of Constraint Programming (CP) solvers is highly sensitive to modeling choices, such as sy…
AI不再只解数学题，开始向黎曼猜想级难题发起进攻，这项框架研究或开启自动发现猜想时代
arXiv:2607.28632v1 Announce Type: new Abstract: Major mathematical conjectures still depend heavily on expert intuition, so a unified method for the s…
OpenAI用GPT-5.5 Pro自动反驳数学猜想，AI在数论领域再次突破。
arXiv:2607.20525v1 Announce Type: new Abstract: OpenAI's recent disproof of the Erd\H{o}s unit distance conjecture marked a milestone for AI in mathem…
用LLM自动发明谓词，突破归纳逻辑编程瓶颈，让AI学会更灵活的推理规则。
arXiv:2607.01585v1 Announce Type: cross Abstract: Predicate invention (PI), the creation of new predicates to extend the hypothesis space, remains a c…
大模型数学证明迎来新解法：Dafny自动验证加持，让AI每一步推理都可机器校验，从「猜」到「证」的关键跨越。
arXiv:2512.10187v3 Announce Type: replace Abstract: LLMs excel at reasoning, but validating their steps remains challenging. Formal verification offer…
从奥数金牌到 Erdős 难题，一页看清 AI 在数学研究的最新水位，数学爱好者别错过。
Article URL: https://stunning-naiad-817d91.netlify.app Comments URL: https://news.ycombinator.com/item?id=48644756 Points: 2 # Comments: 1
来自78个真实GitHub项目的动态基准，挑战AI证明器解决实际数学定理的能力
arXiv:2603.02668v2 Announce Type: replace Abstract: We present SorryDB, a dynamically-updating benchmark of open Lean tasks drawn from 78 real world f…
让大语言模型的反馈“蒸馏”成更智能的Lean定理证明能力，突破自动推理新边界。
arXiv:2605.30861v1 Announce Type: new Abstract: Post-training for reasoning models typically combines supervised fine-tuning with reinforcement learni…
LLM不仅能对话，还能当规划师：用生成启发式破解HTN规划难题，效率与鲁棒性双提升
arXiv:2605.07707v2 Announce Type: replace Abstract: HTN planning is a variation of classical planning where, instead of searching for a linear sequenc…
提出基于智能体的分离逻辑规范自动合成方法，为程序验证与逻辑推理提供新思路。
arXiv:2605.27531v1 Announce Type: cross Abstract: Specification synthesis, the task of automatically inferring formal specifications from program impl…
探讨形式定理证明中对称性的选择，为自动推理提供新视角。
arXiv:2605.22257v1 Announce Type: cross Abstract: Formal theorem provers based on large language models (LLMs) are highly sensitive to superficial var…
提出ACIL方法，自动化链式思维推理与上下文学习结合，提升LLM多步推理能力。
arXiv:2605.17088v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have shown that Chain-of-Thought (CoT) reasoning can s…
提出用LLM生成猜想并转化为Lean形式化验证，基于平方和证书实现自动多项式不等式证明，开辟数学推理新路径。
arXiv:2605.15445v1 Announce Type: new Abstract: Automated proving of polynomial inequalities is a fundamental challenge in automated mathematical reas…