arXiv论文阅读助手 - 自动下载解析LaTeX源码，生成技术摘要与nanochat应用建议

read-arxiv-paper by karpathy/nanochat

849 周安装量

50,200 GitHub Stars

GitHub

安装命令

npx skills add https://github.com/karpathy/nanochat --skill read-arxiv-paper

AI/机器学习自动化自然语言处理

🇨🇳中文介绍

你将获得一个 arXiv 论文的 URL，例如：

https://www.arxiv.org/abs/2601.07372

第一部分：规范化 URL

目标是获取论文的 TeX 源代码（而非 PDF！），URL 通常如下所示：

https://www.arxiv.org/src/2601.07372

注意 URL 中的 /src/。一旦你获得了 URL：

第二部分：下载论文源代码

将 URL 的内容获取到本地的 .tar.gz 文件。一个合适的位置是 ~/.cache/nanochat/knowledge/{arxiv_id}.tar.gz。

（如果文件已存在，则无需重新下载）。

第三部分：在该文件夹中解压文件

将内容解压到 ~/.cache/nanochat/knowledge/{arxiv_id} 目录中。

第四部分：定位入口点

每个 LaTeX 源代码通常都有一个入口点，例如 main.tex 或类似的文件。

第五部分：阅读论文

一旦找到入口点，读取其内容，然后递归地遍历所有其他相关的源文件来阅读论文。

广告位招租

在这里展示您的产品或服务

触达数万 AI 开发者，精准高效

联系我们

🇺🇸English

You will be given a URL of an arxiv paper, for example:

https://www.arxiv.org/abs/2601.07372

Part 1: Normalize the URL

The goal is to fetch the TeX Source of the paper (not the PDF!), the URL always looks like this:

https://www.arxiv.org/src/2601.07372

Notice the /src/ in the url. Once you have the URL:

Part 2: Download the paper source

Fetch the url to a local .tar.gz file. A good location is ~/.cache/nanochat/knowledge/{arxiv_id}.tar.gz.

(If the file already exists, there is no need to re-download it).

Part 3: Unpack the file in that folder

Unpack the contents into ~/.cache/nanochat/knowledge/{arxiv_id} directory.

Part 4: Locate the entrypoint

Every latex source usually has an entrypoint, such as main.tex or something like that.

Part 5: Read the paper

Once you've found the entrypoint, Read the contents and then recurse through all other relevant source files to read the paper.

Part 6: Report

Once you've read the paper, produce a summary of the paper into a markdown file at ./knowledge/summary_{tag}.md. Notice that 1) use the local knowledge directory here (it's easier for me to open and reference here), not in ~/.cache, and 2) generate some reasonable tag like e.g. conditional_memory or whatever seems appropriate given the paper. Probably make sure that the tag doesn't exist yet so you're not overwriting files.

As for the summary itself, remember that you're processing this paper within the context of the nanochat repository, so most often we we will be interested in how to apply the paper and its lessons to the nanochat project. Therefore, you should feel free to "remind yourself" of the related nanochat code by reading the relevant parts, and then explicitly make the connection of how this paper might relate to nanochat or what are things we might be inspired about or try.

Weekly Installs

849

Repository

karpathy/nanochat

GitHub Stars

50.2K

First Seen

Jan 29, 2026

Security Audits

Gen Agent Trust HubPass SocketPass SnykWarn

Installed on

codex792

opencode788

gemini-cli772

github-copilot755

cursor739

kimi-cli732