arxiv-api
安装方式
先用 Prompt 核对来源,也可切换到安装命令或下载可用的安装包。
用 AI 助手安装
复制提示词,让助手先核对固定版本和依赖。
查看 Prompt收起 Prompt
先检查当前 Agent 是否已安装 SkillPI Skill Finder。如果尚未安装,请按官方仓库的说明安装并启用:https://github.com/Findskills/skillpi。然后使用 Skill Finder 打开此 SkillPI 详情页并定位 "arxiv-api":https://skillpi.com/zh/skills/deepskill-8e83a28f5a6bc886ca1a29246efa7b2ddd4162acb65263dd6b3180030bb2f1f3。安装前核对上游来源和版本:https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/43-wentorai-research-plugins/skills/literature/search/arxiv-api/SKILL.md。来源不一致时停止并说明差异。核对通过后,用 Skill Finder 安装目标 Skill,并报告安装路径和来源版本。
此命令从 GitHub 来源仓库获取指定技能。运行前请先查看源文件。
npx skills add https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/tree/bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba/skills/43-wentorai-research-plugins/skills/literature/search/arxiv-api --skill arxiv-api来源与配置
查看 GitHub 源码brycewang-stanford/Auto-Empirical-Research-Skills固定提交 bfa0a6e5a843babbf45a1ef1663fd5dc4f07c0ba
配置方式待核实
请查看原始来源中的适用工具、依赖和权限要求。
安装实测待补充
本条目面向文献与学术工具场景,提供“arxiv-api”技能的目录入口。公开标签:learning、arXiv、预印本、学术搜索。请通过固定上游版本核对实际功能、依赖与权限;此页为 Skillπ 独立编写的用途介绍和原站链接,不代表运行安全保证。原文与附件依各自许可开放。
文件浏览
---
name: arxiv-api
description: "Search and retrieve preprints from the arXiv open-access repository"
metadata:
openclaw:
emoji: "🔍"
category: "literature"
subcategory: "search"
keywords: ["academic database search", "literature search", "scholarly database", "semantic search", "preprint server"]
source: "https://info.arxiv.org/help/api/"
---
# arXiv API Guide
## Overview
The arXiv API provides programmatic access to the arXiv preprint repository, one of the most important open-access archives in the sciences. Founded in 1991, arXiv hosts over 2.4 million scholarly articles across physics, mathematics, computer science, quantitative biology, quantitative finance, statistics, electrical engineering and systems science, and economics.
Researchers use the arXiv API to build literature review tools, monitor new submissions in their fields, and integrate preprint search into automated research workflows. The API returns results in Atom XML format with rich metadata including titles, authors, abstracts, categories, DOIs, and journal references.
The API is free to use with no authentication required. It supports complex boolean queries across multiple fields and allows sorting by relevance, submission date, or last-updated date.
## Authentication
No authentication required. The arXiv API is fully open. However, users must respect the rate limit of 3 requests per second. Excessive usage may result in temporary IP-based blocking. Including a descriptive User-Agent header is considered good practice.
## Using the `search_arxiv` Tool
**IMPORTANT:** When calling the `search_arxiv` tool, use parameter name `query` (NOT
`search_query`). The raw API uses `search_query`, but the tool wrapper accepts `query`.
```
search_arxiv({ query: "ti:transformer AND cat:cs.CL", sort_by: "submittedDate" })
```
## Core Endpoints (Raw API Reference)
### Query: Search for Articles
- **URL**: `GET http://export.arxiv.org/api/query`
- **Parameters** (raw API — the `search_arxiv` tool wraps these automatically):
| Param | Type | Required | Description |
|-------|------|----------|-------------|
| search_query | string | Yes | Query string using arXiv field prefixes (ti, au, abs, cat, id) |
| id_list | string | No | Comma-separated arXiv IDs for direct lookup |
| start | integer | No | Starting index for pagination (default: 0) |
| max_results | integer | No | Number of results to return (default: 10, max: 30000) |
| sortBy | string | No | Sort field: relevance, lastUpdatedDate, submittedDate |
| sortOrder | string | No | ascending or descending |
- **Example**:
```bash
curl "http://export.arxiv.org/api/query?search_query=au:hinton+AND+ti:deep+learning&start=0&max_results=5&sortBy=submittedDate&sortOrder=descending"
```
- **Response**: Atom XML feed with `<entry>` elements containing `<title>`, `<summary>`, `<author>`, `<arxiv:primary_category>`, `<published>`, `<updated>`, and `<link>` fields.
### ID Lookup: Retrieve Specific Papers
- **URL**: `GET http://export.arxiv.org/api/query`
- **Parameters**:
| Param | Type | Required | Description |
|-------|------|----------|-------------|
| id_list | string | Yes | Comma-separated arXiv IDs (e.g., 2301.00001,2301.00002) |
| max_results | integer | No | Number of results to return |
- **Example**:
```bash
curl "http://export.arxiv.org/api/query?id_list=2301.07041&max_results=1"
```
- **Response**: Atom XML feed with full metadata for the requested paper(s).
## Rate Limits
The arXiv API enforces a rate limit of 3 requests per second. There is no daily request cap, but automated bulk downloading should be done using the arXiv bulk data access options instead of the API. If you exceed the rate limit, you will receive HTTP 503 responses. Implement exponential backoff and a minimum 3-second delay between requests to avoid being temporarily blocked.
## Common Patterns
### Monitor New Submissions in a Category
Track daily submissions in a specific arXiv category by querying with a date range and category filter:
```bash
curl "http://export.arxiv.org/api/query?search_query=cat:cs.AI+AND+submittedDate:[202603010000+TO+202603092359]&sortBy=submittedDate&sortOrder=descending&max_results=50"
```
### Build a Reading List from Keywords
Search across titles and abstracts for specific research topics:
```bash
curl "http://export.arxiv.org/api/query?search_query=(ti:transformer+OR+abs:transformer)+AND+cat:cs.CL&max_results=20&sortBy=relevance"
```
### Batch Metadata Retrieval
Retrieve metadata for multiple known papers in a single request:
```bash
curl "http://export.arxiv.org/api/query?id_list=2301.07041,2302.13971,2303.08774&max_results=3"
```
## References
- Official documentation: https://info.arxiv.org/help/api/
- arXiv API user manual: https://info.arxiv.org/help/api/user-manual.html
- arXiv bulk data access: https://info.arxiv.org/help/bulk_data.html
版本历史
-
v2026.07
GitHub ↗
原版更新说明
## Highlights - **First tagged release.** Every gate is green: `make check` (validate + 183 unit tests + eval-harness + numeric benchmarks), validate-catalog, quality-evals, and OpenSSF Scorecard on `main`. - **Rigor double loop at 13 method families.** Each family closes taxonomy tag → eval scenario (does the agent avoid the method's known traps?) → deterministic numeric benchmark (does it recover the true effect?). New this cycle: heterogeneous treatment effects (CATE) and quantile treatment effects (QTE). - **Paper-WorkFlow flagship at 29/29 executable rigor gates**, now merged to its `main` with a drift-gated README badge — the credibility artifact is checked by CI, so it can never silently go stale ([RIGOR.md](https://github.com/brycewang-stanford/Paper-WorkFlow/blob/main/RIGOR.md)). - **1,150 vendored skills / 69 collections**, all license-audited, security-scanned, tracked in a machine-readable catalog with CI-enforced freshness, and importable as a single whole-repo router skill. - **Hardened weekly upstream syncs**: synced trees must pass the full gate before merge; this cycle both sync PRs were verified, patched (StatsPAI's SkillOpt execution-gate card restored), and merged. - **First-party plugin marketplace** (Python / R / Stata empirical-analysis plugins + guide) shipped in the previous cycle, now under a tagged version. ## Known Follow-Ups - Ecosystem benchmark comparison (AERS vs econometrics agents on the shared benchmark suite) — [PLAN-2026-07 week 3](https://github.com/brycewang-stanford/Auto-Empirical-Research-Skills/blob/main/docs/PLAN-2026-07.md). - Decomposition (Oaxaca–Blinder) and shift-share (Bartik) method families (weeks 3–4). - GitHub Pages catalog site, README demo screenshots, five-language README consistency script (week 4). ## Catalog - Top-level collections: **69** - `SKILL.md` files: **1150** - Cataloged agent tools: **335** ([`tools/CATALOG.md`](../tools/CATALOG.md)) ## Methodological rigor - Method families in the coverage map: **13** ([`RIGOR_COVERAGE.md`](RIGOR_COVERAGE.md)) - Eval scenarios: **26** (138 rubric items, 122 auto-checkable) ([`../eval-harness/`](../eval-harness/README.md)) - Benchmark tasks: **13** (70 gold checks, 58 required) ([`../benchmark/`](../benchmark/README.md)) ### Method families (skills tagged) - `iv`: 27 - `rdd`: 25 - `panel-fe`: 19 - `staggered-did`: 17 - `bayesian`: 13 - `did`: 10 - `event-study`: 10 - `matching`: 10 - `synthetic-control`: 10 - `cate`: 8 - `dml`: 8 - `survival`: 3 - `quantile`: 2 ### Eval scenarios by category - `causal-identification`: 14 - `citation-hygiene`: 1 - `reproducibility`: 2 - `research-integrity`: 1 - `runtime-safety`: 1 - `statistical-validity`: 2 - `writing-compliance`: 3 - `writing-style`: 2 ## License buckets - AGPL-3.0: 1 - Apache-2.0: 1 - CC-BY-NC-4.0 (non-commercial): 1 - CC-BY-SA-4.0: 1 - CC-BY-SA-4.0 (repository default): 4 - GPL-3.0: 1 - MIT: 35 - MIT Non-Commercial: 1 - Mixed (per-skill; see folder): 2 - UNKNOWN - check upstream: 22 ## Quality gates - `make check` — catalog/provenance/audit/eval freshness, repo hygiene, Paper-WorkFlow gates, stdlib unit tests, eval-harness lint + graded smoke, and the strict numeric benchmark (reference-gold drift fails the build). - External links and OpenSSF Scorecard run on their scheduled workflows.
当前收录版本
0.0.1
质量评测
满分 100。前四项来自 DeepSkill 收录的质量报告。
评分依据
提供arXiv预印本搜索与检索功能,满足学术研究人员文献调研和跟踪新论文的高频刚需
评分依据
description清晰准确,frontmatter中keywords覆盖充分,包括'academic database search'、'literature search'等精准术语
评分依据
文档结构完整,包含Overview、Authentication、Tool Usage、Core Endpoints、Rate Limits、Common Patterns、References等必要章节
评分依据
工具来源明确(arXiv官方API),参数说明准确,强调rate limit和User-Agent最佳实践
计算方式
取前四项原始分值的算术平均,四舍五入取整。可通过收录报告核对各项评分与说明,运行记录需单独查证。
权限与使用前检查
根据当前主文档自动整理,命中内容可能是示例或防护说明;不是实际权限声明,也未覆盖附件、外部依赖或运行行为。
未从主文档识别到上述常见操作,不能据此判断无需权限或没有风险。
文档引用的域名或地址
这些地址可能用于文档链接或示例,不是已批准的联网清单。使用前核对实际目的地及发送的数据。
- export.arxiv.org
- info.arxiv.org
安全评级与访问范围
risk · 静态证据核验,不代表运行安全保证。
使用前请由宿主核对并授权实际文件读写、外部服务和联网目的地;本站的核验不会授予任何运行权限。
用户讨论
还没有已核实的点评。