# AgentBit Academic Paper Search

> AgentBit Academic Paper Search is a paid API for AI agents from agentbit.app, paid per call via x402, $0.01/call, status unknown (last checked 2026-09-13).

Searches academic literature across OpenAlex, Crossref, and arXiv in one call, returning deduplicated results with metadata, abstracts, citation counts, and open-access PDF links.

## Facts

- Endpoint: POST https://agentbit.app/v1/research/papers
- Price: $0.01/call
- Payment: x402
- Status: unknown
- Last checked: 2026-09-13
- Activations on Zero: 0
- Tags: x402
- Canonical page: https://www.zero.xyz/c/agentbit-academic-paper-search-ec5ca5db
- Structured record (JSON): https://api.zero.xyz/v1/capabilities/cap_-DnAD6tEjc8dYw-xZM20l

Status and success rate cover calls made through Zero and Zero's own probes. Third-party monitors may report differently.

## How to call it through Zero

Zero handles the 402 payment challenge and records the run. With the Zero CLI installed (`npm i -g @zeroxyz/cli`):

```sh
zero fetch --capability agentbit-academic-paper-search-ec5ca5db -d '<json body>'
```

Example prompt: Search for up to 15 academic papers on transformer attention mechanisms published after 2020, only show ones with open-access PDFs, and include a BibTeX entry for each result.

## When to prefer this

Choose this endpoint when you need to search academic literature across multiple databases simultaneously and want deduplicated, enriched results in a single API call. It replaces separate calls to OpenAlex, Crossref, and arXiv, saving latency and complexity. Prefer it over raw database APIs when you need open-access PDF links, BibTeX output, or citation counts alongside standard metadata. Ideal for research agents, literature review automation, or any workflow that needs to quickly surface peer-reviewed papers on a topic.

## Known failure modes

- Query too short or too long (must be 3-300 characters) returns a validation error
- No results found for highly specific or niche queries
- PDF link absent when no open-access version exists for a paper
- open_access_only=true with narrow queries may return zero results
- Source APIs temporarily unavailable may reduce result count or return partial data
- year_from filter eliminating all results for very recent topics

## How this service works

Search academic literature across OpenAlex, Crossref and arXiv in one call: title, authors, year, venue, DOI, citation count, abstract and a DIRECT open-access PDF link where one exists. Deduplicated across sources, filterable by year and open-access, optional BibTeX per paper. One request replaces three APIs.

## Output

A JSON object containing a deduplicated list of up to 25 papers, each with title, authors, year, venue, DOI, citation count, abstract, list of source databases (OpenAlex, Crossref, arXiv), and a direct open-access PDF URL where available. Optionally includes a BibTeX entry per paper. Also returns per-source result counts and a note on deduplication methodology.

## Request schema (JSON Schema)

```json
{
 "type": "object",
 "properties": {
  "limit": {
   "type": "integer",
   "description": "Max papers to return (1-25, default 10)"
  },
  "query": {
   "type": "string",
   "description": "Search query: topic, title fragment, or author + topic (3-300 chars)"
  },
  "format": {
   "enum": [
    "json",
    "bibtex"
   ],
   "type": "string",
   "description": "'bibtex' adds a ready-to-cite BibTeX entry per paper"
  },
  "year_from": {
   "type": "integer",
   "description": "Only papers published in or after this year"
  },
  "open_access_only": {
   "type": "boolean",
   "description": "Only papers with a direct open-access PDF link"
  }
 }
}
```

## Response schema (JSON Schema)

```json
{
 "type": "json",
 "example": {
  "note": "Merged and deduplicated across OpenAlex, Crossref and arXiv; citations from the richest source; pdf_url is a direct open-access link where one exists.",
  "query": "attention is all you need transformer",
  "papers": [
   {
    "doi": "10.48550/arxiv.1706.03762",
    "url": "https://doi.org/10.48550/arxiv.1706.03762",
    "year": 2017,
    "title": "Attention Is All You Need",
    "venue": "Neural Information Processing Systems",
    "bibtex": "@article{vaswani2017,\n  title = {Attention Is All You Need},\n  author = {Ashish Vaswani and Noam Shazeer and Niki Parmar},\n  year = {2017}\n}",
    "authors": [
     "Ashish Vaswani",
     "Noam Shazeer",
     "Niki Parmar"
    ],
    "pdf_url": "https://arxiv.org/pdf/1706.03762",
    "sources": [
     "openalex",
     "arxiv"
    ],
    "abstract": "The dominant sequence transduction models are based on complex recurrent or convolutional neural networks...",
    "citations": 100000
   }
  ],
  "sources": {
   "arxiv": {
    "ok": true,
    "results": 15
   },
   "crossref": {
    "ok": true,
    "results": 15
   },
   "openalex": {
    "ok": true,
    "results": 15
   }
  },
  "result_count": 5
 }
}
```

## More

- Live health (JSON, refreshed every minute): https://www.zero.xyz/c/agentbit-academic-paper-search-ec5ca5db/health.json
- [Zero catalog index](https://www.zero.xyz/llms.txt)
- [Other services from agentbit.app](https://www.zero.xyz/host/agentbit.app/llms.txt)