> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentkey.app/llms.txt
> Use this file to discover all available pages before exploring further.

# Academic

> Papers, researchers, institutions, venues and patents.

The **Academic** category lets an agent do literature work: search and rank
papers on a topic, open a paper's content and ask questions of its PDF, follow
citations, profile a researcher or an institution, browse a venue's output, and
look up patents — from two providers.

## Explore

> **[Papers](/capabilities/academic/papers)**
>
> arXiv and AMiner paper search and details.

> **[Researchers and institutions](/capabilities/academic/researchers-and-institutions)**
>
> Scholars, institutions, venues and patents.

## Providers

| Provider | Coverage |
| - | - |
| **AMiner** | Papers: search by title or by title / keyword / abstract / author / institution / venue, paper detail, citation list, batch paper info, recommendations by topic or scholar. Scholars: search, detail, research profile (interests, fields, structured career and education), papers, patents, projects, statistics (paper count, citations, h-index, g-index). Organizations: search, name disambiguation, detail, papers, patents, scholars. Venues: search, detail, papers by year. Patents: search, detail, brief info |
| **alphaxiv** | `discover_papers` ranks candidate papers for a research topic; `get_paper_content` and `answer_pdf_queries` return a paper's content or the pages relevant to a question (by id, URL or title); `find_researchers`, `resolve_researchers`, `get_researcher` and `get_researcher_papers` profile researchers; `read_files_from_github_repository` reads a paper's code repository |
| **alphaxiv-api** | alphaXiv's public REST API, by arXiv id: paper metadata with authors, abstract, first submission date and links (`getPaperMetadata`); a compact record with the citation count alphaXiv tracks (`getPaper`); the resolved reference list with each cited paper's arXiv id and DOI where known (`getPaperReferences`) |

AMiner tools return gateway-wrapped JSON with the payload under `data`; most
detail tools take an AMiner id, so start from a `search_*` tool. AMiner
summaries are in Chinese; `find_tools(q=...)` matches them in either language.
The per-call cost is shown by `describe_tool`.

> [!NOTE]
>
> **Building with code?** Developers and enterprise integrations can call this
> category through [Scenario Methods](/api-reference/scenario/overview): fixed
> REST contracts with a stable schema, a fixed price and automatic provider
> failover. The methods are listed by platform in the API Reference sidebar.

## Browse the catalog

```text theme={null}
find_tools(prefix="academic")
find_tools(q="recent papers on speculative decoding for LLM inference")
describe_tool("alphaxiv/discover_papers")
execute_tool("alphaxiv/discover_papers", { ...params })   # copy describe_tool's execute_as
```

> [!TIP]
>
> Google Scholar results are also reachable through `Serper/searchScholar` in
> the [Search](/capabilities/search) category, and patents through
> `Serper/searchPatents`.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.