FARMS：面向自动化计算科学的可验证知识基础
FARMS: A Verifiable Foundation for Automated Computational Science
AI 导读
FARMS 是一个将计算数学转化为 AI 可用计算知识的可验证基础框架，通过源准备、可复用表示与语义审查，把形式化陈述与源上下文、算法含义及定量保证相连接。在随机数值线性代数和数值偏微分方程的 171 个目标中，157 个通过流水线，每个目标的平均估计成本为 $0.85-2.29。该框架经 Lean 检查的推导由热流求解和波响应压缩示例说明，可为可信的自动化计算科学提供低成本、可复用的知识基础。
正文 · 原文
Abstract:Automated computational science could accelerate discovery by selecting, adapting and developing numerical methods. This prospect requires mathematical knowledge that AI systems can interpret and reuse with explicit guarantees. Here we present FARMS, a faithful and efficient foundation that transforms computational mathematics into AI-ready computing knowledge. FARMS connects formal statements to source context, algorithmic meaning and quantitative guarantees through source preparation, reusable representations and semantic review. Across 171 targets in randomized numerical linear algebra and numerical partial differential equations, 157 were accepted by the pipeline, with mean estimated costs of US \$0.85-2.29 per target across sources. Lean-checked implications from explicit source premises connect selected statements to computational skills, illustrated by a heat-flow solve and wave-response compression. FARMS therefore supports an affordable, reusable knowledge foundation for trustworthy automated computational science.
| Subjects: | Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO) |
| Cite as: | arXiv:2610.40560 [cs.AI] |
| (or arXiv:2610.40560v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.40560 arXiv-issued DOI via DataCite |
Submission history
From: Di Wu [view email]
[v1]
Thu, 29 Oct 2026 17:40:57 UTC (1,079 KB)
来源：arXiv cs.AI · arxiv.org