alphaxiv

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

AlphaXiv Paper Lookup

AlphaXiv 单篇论文查询

Lookup paper: $ARGUMENTS

Quick single-paper reader with tiered source fallback (overview → full markdown → LaTeX source). Powered by AlphaXiv.

查询论文：$ARGUMENTS

具备分层源回退功能的快速单篇论文阅读器（概述 → 完整markdown → LaTeX源码）。由AlphaXiv提供支持。

Role & Positioning

角色与定位

This skill is the quick single-paper reader that returns LLM-optimized summaries:

Skill	Source	Best for
`/arxiv`	arXiv API	Batch search, PDF download, metadata
`/deepxiv`	DeepXiv SDK	Progressive section-level reading
`/semantic-scholar`	S2 API	Published venue metadata, citation counts
`/alphaxiv`	alphaxiv.org	Instant LLM-optimized summary of one paper, with LaTeX source fallback

Do NOT use this skill for topic discovery, broad literature search, or multi-paper surveys — use

/research-lit

/arxiv

instead.

该技能是一款快速单篇论文阅读器，可返回经LLM优化的摘要：

技能	数据源	适用场景
`/arxiv`	arXiv API	批量搜索、PDF下载、元数据获取
`/deepxiv`	DeepXiv SDK	渐进式章节级阅读
`/semantic-scholar`	S2 API	已发表期刊元数据、引用次数统计
`/alphaxiv`	alphaxiv.org	单篇论文的即时LLM优化摘要，支持LaTeX源码回退

请勿将此技能用于主题发现、广泛文献搜索或多篇论文调研——请改用

/research-lit

或

/arxiv

。

Constants

常量定义

OVERVIEW_URL =

https://alphaxiv.org/overview/{PAPER_ID}.md

ABS_URL =
```
https://alphaxiv.org/abs/{PAPER_ID}.md
```
ARXIV_SRC_URL =
```
https://arxiv.org/src/{PAPER_ID}
```

Overrides (append to arguments):
/alphaxiv 2401.12345
— quick overview
/alphaxiv "https://arxiv.org/abs/2401.12345"
— auto-extract ID
/alphaxiv 2401.12345 - depth: src
— force LaTeX source inspection
/alphaxiv 2401.12345 - depth: abs
— force full markdown

OVERVIEW_URL =

https://alphaxiv.org/overview/{PAPER_ID}.md

ABS_URL =
```
https://alphaxiv.org/abs/{PAPER_ID}.md
```
ARXIV_SRC_URL =
```
https://arxiv.org/src/{PAPER_ID}
```

参数覆盖（追加至参数后）：
/alphaxiv 2401.12345
—— 快速获取概述
/alphaxiv "https://arxiv.org/abs/2401.12345"
—— 自动提取ID
/alphaxiv 2401.12345 - depth: src
—— 强制查看LaTeX源码
/alphaxiv 2401.12345 - depth: abs
—— 强制获取完整markdown内容

Workflow

工作流程

Step 1: Parse Arguments & Extract Paper ID

步骤1：解析参数并提取论文ID

Parse

$ARGUMENTS

to extract a bare arXiv paper ID. Accept these input formats:

https://arxiv.org/abs/2401.12345

https://arxiv.org/abs/2401.12345v2

```
https://arxiv.org/pdf/2401.12345
```

https://alphaxiv.org/overview/2401.12345

```
https://alphaxiv.org/abs/2401.12345
```
```
2401.12345
```
or
```
2401.12345v2
```

Strip version suffixes (

v1

v2

, ...) for API calls. Store as

PAPER_ID

Parse optional directives:

- depth: overview|abs|src
: force a specific tier instead of cascading

解析

$ARGUMENTS

以提取纯arXiv论文ID。支持以下输入格式：

https://arxiv.org/abs/2401.12345

或

https://arxiv.org/abs/2401.12345v2

```
https://arxiv.org/pdf/2401.12345
```

https://alphaxiv.org/overview/2401.12345

```
https://alphaxiv.org/abs/2401.12345
```
```
2401.12345
```
或
```
2401.12345v2
```

移除版本后缀（

v1

、

v2

等）以用于API调用，将结果存储为

PAPER_ID

。

解析可选指令：

- depth: overview|abs|src
：强制使用特定层级，而非逐层降级

Step 2: Fetch AlphaXiv Overview (Tier 1 — Fastest)

步骤2：获取AlphaXiv概述（层级1 —— 最快）

Fetch the structured overview from

https://alphaxiv.org/overview/{PAPER_ID}.md

This returns a structured, LLM-optimized report designed for machine consumption. Use this as the default and preferred source.

If the overview answers the user's question, stop here. Do not fetch deeper tiers unnecessarily.

If the request fails (HTTP 404 — paper not yet processed) or the content is insufficient, proceed to Step 3.

从

https://alphaxiv.org/overview/{PAPER_ID}.md

获取结构化概述。

该接口返回一份结构化、经LLM优化的报告，专为机器处理设计。默认优先使用此数据源。

如果概述已能回答用户问题，在此步骤停止。无需不必要地获取更深层级的内容。

若请求失败（HTTP 404 —— 论文尚未处理）或内容不足以回答问题，进入步骤3。

Step 3: Fetch Full AlphaXiv Markdown (Tier 2 — More Detail)

步骤3：获取完整AlphaXiv Markdown内容（层级2 —— 更详细）

Fetch the full paper markdown from

https://alphaxiv.org/abs/{PAPER_ID}.md

This provides the full paper body as markdown. Use when the user needs:

Specific methodology details
Detailed experimental results
Particular sections not covered in the overview

If this still does not answer the question, proceed to Step 4.

从

https://alphaxiv.org/abs/{PAPER_ID}.md

获取完整论文的markdown内容。

当用户需要以下信息时使用此层级：

具体方法论细节
详细实验结果
概述未覆盖的特定章节

若此层级仍无法回答问题，进入步骤4。

Step 4: Fetch arXiv LaTeX Source (Tier 3 — Deepest)

步骤4：获取arXiv LaTeX源码（层级3 —— 最深入）

When the overview and full markdown are both insufficient (e.g., the user asks about equations, proofs, appendix details, or implementation specifics), download the paper's LaTeX source from

https://arxiv.org/src/{PAPER_ID}

The source is a

.tar.gz

archive. Download it to a temporary directory, extract it, and list the

.tex

files inside.

Then inspect only the files needed to answer the question. Prioritize:

Top-level
```
*.tex
```
files (usually the main document)
Files referenced by
```
\input{}
```
or
```
\include{}
```
Appendices, tables, or sections directly related to the user's question

Do NOT read the entire source tree by default. Read selectively.

Temporary source artifacts live under

/tmp

. Do not rely on persistence.

当概述和完整markdown内容均不足以回答问题时（例如用户询问公式、证明、附录细节或实现规范），从

https://arxiv.org/src/{PAPER_ID}

下载论文的LaTeX源码。

源码为

.tar.gz

压缩包。将其下载至临时目录，解压后列出其中的

.tex

文件。

然后仅检查回答问题所需的文件。优先级如下：

顶层
```
*.tex
```
文件（通常为主文档）
```
\input{}
```
或
```
\include{}
```
引用的文件
与用户问题直接相关的附录、表格或章节

默认请勿读取整个源码树。仅选择性读取。

临时源码文件存储在

/tmp

目录下，不保证持久化。

Step 5: Present Results

步骤5：呈现结果

Default Answer Shape

默认回答格式

markdown

undefined

markdown

undefined

[Paper Title]

[论文标题]

arXiv: [PAPER_ID] — https://arxiv.org/abs/[PAPER_ID]
Source depth: overview | abs | src

arXiv：[PAPER_ID] —— https://arxiv.org/abs/[PAPER_ID]
数据源层级：overview | abs | src

Summary

摘要

[2-3 sentence summary]

[2-3句话的摘要]

Key Points

核心要点

[point 1]
[point 2]
[point 3]

[要点1]
[要点2]
[要点3]

Answer to Your Question

您的问题解答

[Direct answer if the user asked a specific question]


If the user only asks for one specific detail, answer it directly — skip the full template.

[若用户提出了具体问题，此处给出直接回答]


若用户仅询问某一特定细节，直接回答即可——无需使用完整模板。

Suggest Follow-Up Skills

Update Research Wiki (if active)

更新研究维基（若已启用）

Required when
research-wiki/
exists in the project; skip silently otherwise. After presenting the paper summary, ingest the single paper that was read:

if [ -d research-wiki/ ]:
    python3 tools/research_wiki.py ingest_paper research-wiki/ \
        --arxiv-id "<paper_arxiv_id>" \
        [--thesis "<one-line thesis from the Tier 1 overview>"]

The helper handles metadata fetch, slug, dedup, page creation, index rebuild, and log append — do not handwrite
papers/<slug>.md
. See

shared-references/integration-contract.md

. If wiki was not present at read time, the user can backfill via

python3 tools/research_wiki.py sync research-wiki/ --arxiv-ids <id>

当项目中存在
research-wiki/
目录时必须执行；否则静默跳过。在呈现论文摘要后，将读取的单篇论文纳入维基：

if [ -d research-wiki/ ]:
    python3 tools/research_wiki.py ingest_paper research-wiki/ \
        --arxiv-id "<paper_arxiv_id>" \
        [--thesis "<来自层级1概述的一句话核心论点>"]

该辅助工具会处理元数据获取、slug生成、去重、页面创建、索引重建及日志追加——请勿手动编写
papers/<slug>.md
。详见

shared-references/integration-contract.md

。若读取时维基不存在，用户可通过

python3 tools/research_wiki.py sync research-wiki/ --arxiv-ids <id>

进行补录。

Key Rules

核心规则

Overview first:
```
overview
```
is the fastest path and must always be tried before deeper tiers. Only escalate when needed.
Minimal reads: At
```
src
```
tier, read only the files that answer the question. Full-tree reads waste tokens.
Cross-platform: When downloading and extracting the source archive, prefer cross-platform approaches (e.g., Python stdlib) over platform-specific commands to ensure Windows/WSL compatibility.
No PDF parsing: This skill reads structured markdown and LaTeX source, not raw PDFs. For PDF content, suggest
```
/arxiv
```
with download.
Rate limiting: arXiv source download may rate-limit. If HTTP 429 occurs, wait 5 seconds and retry once. If still blocked, report the error and suggest
```
/deepxiv
```
as alternative.
Complementary, not competing: This skill complements
```
/arxiv
```
(search + download) and
```
/deepxiv
```
(progressive reading). Do not re-implement their functionality.

优先使用概述：
```
overview
```
是最快路径，必须在尝试更深层级前优先使用。仅在必要时升级层级。
最小化读取：在
```
src
```
层级，仅读取回答问题所需的文件。读取整个源码树会浪费token。
跨平台兼容：下载并解压源码压缩包时，优先使用跨平台方案（例如Python标准库）而非平台特定命令，以确保Windows/WSL兼容性。
不解析PDF：该技能读取结构化markdown和LaTeX源码，而非原始PDF。如需PDF内容，推荐使用带下载参数的
```
/arxiv
```
。
速率限制：arXiv源码下载可能触发速率限制。若出现HTTP 429错误，等待5秒后重试一次。若仍被拦截，报告错误并推荐使用
```
/deepxiv
```
作为替代方案。
互补而非竞争：该技能是
```
/arxiv
```
（搜索+下载）和
```
/deepxiv
```
（渐进式阅读）的补充。请勿重复实现它们的功能。

Integration with Other Skills

与其他技能的集成

As enrichment in

/research-lit

在

/research-lit

中作为增强步骤

/research-lit

can use this skill's Tier 1 (overview) as a fast enrichment step between search and deep analysis. After finding arXiv papers in Step 1, fetch AlphaXiv overviews to quickly assess relevance before committing to full-text reads:

Step 1: Search → list of arXiv IDs
Step 1.5: AlphaXiv overview for top 5-8 papers (this skill, Tier 1 only)
Step 2: Deep analysis only for papers that pass the relevance filter

This saves significant tokens by filtering out marginally relevant papers before deep reading.

/research-lit

可将此技能的层级1（概述）用作搜索与深度分析之间的快速增强步骤。在步骤1找到arXiv论文后，获取AlphaXiv概述以快速评估相关性，再决定是否进行全文阅读：

步骤1：搜索 → 得到arXiv ID列表
步骤1.5：为排名前5-8的论文获取AlphaXiv概述（本技能，仅层级1）
步骤2：仅对通过相关性筛选的论文进行深度分析

通过在深度阅读前过滤掉相关性较低的论文，可大幅节省token消耗。

As follow-up from other skills

作为其他技能的后续操作

After

/research-lit

/novelty-check

, or

/idea-discovery

surface a specific paper, users can invoke

/alphaxiv PAPER_ID

for a fast deep-dive without re-running the full survey.

在

/research-lit

、

/novelty-check

或

/idea-discovery

定位到某篇特定论文后，用户可调用

/alphaxiv PAPER_ID

进行快速深入分析，无需重新运行完整调研。