# Academic Paper Search API — arXiv + Semantic Scholar | $0.05 (`devsef/academic-paper-search`) Actor

Search academic papers across arXiv and Semantic Scholar with one query. Deduplicated, normalized results with title, authors, year, abstract, citations and PDF links — ready for AI agents, RAG pipelines and literature reviews. Flat $0.05 per search.

- **URL**: https://apify.com/devsef/academic-paper-search.md
- **Developed by:** [Steffano van Hoven](https://apify.com/devsef) (community)
- **Categories:** AI, Developer tools
- **Stats:** 1 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks
- **User rating**: No ratings yet

## Pricing

from $50.00 / 1,000 search completeds

This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage.

Learn more: https://docs.apify.com/actors/running/actors-in-store.md#pay-per-event

## What's an Apify Actor?

Actors are web data automations that power AI and operations. They run on the Apify platform to scrape websites, process data, connect APIs, and automate workflows.
In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours,
and optionally produces a well-defined JSON output, datasets with results, or files in key-value store.
In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server.
Actors are written with capital "A".

## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
The best way to integrate Actors is as follows.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For usage examples, see the [API](#api) section below.

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).

# README

### What does Academic Paper Search do?

**Academic Paper Search** searches [arXiv](https://arxiv.org) and [Semantic Scholar](https://www.semanticscholar.org) 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:**

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

### Output

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

```json
[
  {
    "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.

# Actor input Schema

## `query` (type: `string`):

Search term to look up across arXiv and Semantic Scholar, e.g. "large language model agents".

## `maxResults` (type: `integer`):

Maximum number of papers to return after merging and deduplication (1-100).

## `sources` (type: `string`):

Which academic databases to search.

## `yearFrom` (type: `integer`):

Only include papers published in or after this year, e.g. 2020.

## Actor input object example

```json
{
  "query": "large language model agents",
  "maxResults": 20,
  "sources": "both"
}
```

# Actor output Schema

## `papers` (type: `string`):

No description

## `summary` (type: `string`):

No description

# API

You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup.

## JavaScript example

```javascript
import { ApifyClient } from 'apify-client';

// Initialize the ApifyClient with your Apify API token
// Replace the '<YOUR_API_TOKEN>' with your token
const client = new ApifyClient({
    token: '<YOUR_API_TOKEN>',
});

// Prepare Actor input
const input = {
    "query": "large language model agents"
};

// Run the Actor and wait for it to finish
const run = await client.actor("devsef/academic-paper-search").call(input);

// Fetch and print Actor results from the run's dataset (if any)
console.log('Results from dataset');
console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
items.forEach((item) => {
    console.dir(item);
});

// 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs

```

## Python example

```python
from apify_client import ApifyClient

# Initialize the ApifyClient with your Apify API token
# Replace '<YOUR_API_TOKEN>' with your token.
client = ApifyClient("<YOUR_API_TOKEN>")

# Prepare the Actor input
run_input = { "query": "large language model agents" }

# Run the Actor and wait for it to finish
run = client.actor("devsef/academic-paper-search").call(run_input=run_input)

# Fetch and print Actor results from the run's dataset (if there are any)
print(f"💾 Check your data here: https://console.apify.com/storage/datasets/{run.default_dataset_id}")
for item in client.dataset(run.default_dataset_id).iterate_items():
    print(item)

# 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start

```

## CLI example

```bash
echo '{
  "query": "large language model agents"
}' |
apify call devsef/academic-paper-search --silent --output-dataset

```

## MCP server setup

```json
{
    "mcpServers": {
        "apify": {
            "type": "http",
            "url": "https://mcp.apify.com/?tools=fetch-actor-details,devsef/academic-paper-search"
        }
    }
}

```

The hosted server signs you in with OAuth on first connect, so no API token belongs in this config. Clients without OAuth support can send an `Authorization: Bearer <APIFY_API_TOKEN>` header instead, using a token from API & Integrations in Apify Console (https://console.apify.com/settings/integrations).

## OpenAPI specification

Download the OpenAPI definition: https://api.apify.com/v2/actors/ZcZLz8lO3JXx7DQhc/builds/Fw8UaYnVsEuYGU2fV/openapi.json