Academic Paper Search API — arXiv + Semantic Scholar | $0.05

What does Academic Paper Search do?

Academic Paper Search searches arXiv and Semantic Scholar with a single query and returns one clean, deduplicated list of papers. Each result is normalized to the same structure — title, authors, year, abstract, DOI, arXiv id, canonical link, PDF link, and citation count — so you can feed it straight into a spreadsheet, a literature review, or a RAG pipeline without any post-processing.

It is built for researchers who want a quick cross-database overview and for AI agents that need structured paper metadata as a tool call.

Sources

The Actor uses the official public APIs of both services — no scraping, no API keys required:

• arXiv API (export.arxiv.org/api/query) — full-text relevance search over all arXiv preprints.
• Semantic Scholar Graph API (api.semanticscholar.org/graph/v1/paper/search) — search over 200M+ papers with citation counts and open-access PDF links.

Papers found in both databases are merged into a single result (matched by DOI, arXiv id, or normalized title) with "source": "both", keeping the Semantic Scholar citation count and the best available PDF link.

How to use Academic Paper Search

1. Open the Actor in the Apify Console and click Try for free.
2. Enter your Search query (e.g. large language model agents).
3. Optionally set Max results (default 20, max 100), restrict Sources, or set Year from to only get recent papers.
4. Click Start. Results appear in the dataset within seconds.

Input

Field	Type	Required	Default	Description
query	string	yes	—	Search term
maxResults	integer	no	20	Max papers after merge and dedupe (1–100)
sources	string	no	both	both, arxiv, or semanticscholar
yearFrom	integer	no	—	Only papers published in or after this year

Example input:

{
  "query": "large language model agents",
  "maxResults": 20,
  "yearFrom": 2022
}

Output

One dataset item per paper. Real excerpt from a run with the query above:

[
  {
    "title": "A survey on large language model based autonomous agents",
    "authors": ["Lei Wang", "Chengbang Ma", "Xueyang Feng", "..."],
    "year": 2023,
    "abstract": "Autonomous agents have long been a research focus in academic and industry communities...",
    "doi": "10.1007/s11704-024-40231-1",
    "arxivId": "2308.11432",
    "url": "https://www.semanticscholar.org/paper/28c6ac721f54544162865f41c5692e70d61bccab",
    "pdfUrl": "https://doi.org/10.1007/s11704-024-40231-1",
    "citationCount": 3222,
    "source": "semanticscholar"
  },
  {
    "title": "Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents",
    "authors": ["Renxi Wang", "Haonan Li", "Xudong Han", "Yixuan Zhang", "Timothy Baldwin"],
    "year": 2024,
    "abstract": "Large language models (LLMs) have achieved success in acting as agents, which interact with environments through tools such as search engines...",
    "doi": null,
    "arxivId": "2402.11651",
    "url": "http://arxiv.org/abs/2402.11651v2",
    "pdfUrl": "https://arxiv.org/pdf/2402.11651v2",
    "citationCount": null,
    "source": "arxiv"
  }
]

Results are sorted by citation count (highest first); papers without a citation count follow after. A run summary (which sources were used and how many papers each returned) is stored in the key-value store under the SUMMARY key.

You can download the dataset in various formats such as JSON, HTML, CSV, or Excel.

Pricing

This Actor uses pay-per-event pricing: one search-completed event is charged per successful search, regardless of how many papers are returned. Searches that return zero results are free — no delivery, no charge. Failed runs are never charged.

Limitations

• Maximum 100 results per search. For broader coverage, run multiple narrower queries.
• Semantic Scholar rate limits — the public API is shared and occasionally returns HTTP 429. The Actor retries once, then continues with arXiv results only (visible in the SUMMARY). Re-run a few minutes later for full coverage.
• Metadata only — titles, authors, abstracts, and PDF links are returned; the Actor does not download or parse full paper texts.
• Citation counts come from Semantic Scholar — papers found only on arXiv have citationCount: null.

FAQ and support

Why does the same paper sometimes show "source": "both"? It was found in both databases and merged into one entry — you get the arXiv PDF link and the Semantic Scholar citation count together.

Can I use this as a tool for my AI agent? Yes — call the Actor via the Apify API and read the dataset items; the output shape is stable and typed.

For bugs or feature requests, open an issue in the Issues tab.

---

More tools: see my profile.