Add Semantic Scholar to your AI agent
Semantic Scholar is an AI-powered academic search engine that helps researchers discover and understand scientific literature
- Things your agent can do in Semantic Scholar
- 20
Things your AI can do in Semantic Scholar
Your FormWise AI can handle any of these in Semantic Scholar — on its own, without you needing to click a button.
Get paper recommendations
PopularTool to get paper recommendations based on positive and negative example papers. Use when you need to find papers similar to ones you like (positive examples) and optionally dissimilar to ones you don't like (negative examples). The recommendation engine analyzes the provided examples and returns relevant papers from the Semantic Scholar database.
Get recommendations for paper
PopularTool to get recommended papers for a single positive example paper. Use when you need to find papers similar to a given paper based on Semantic Scholar's recommendation algorithm.
Search Bulk Papers
PopularTool to perform bulk search for academic papers. Intended for bulk retrieval of basic paper data without search relevance scoring. Use when you need to retrieve large sets of papers with optional text filtering and various criteria. Supports token-based pagination for efficient fetching of up to 10 million papers (use Datasets API for larger needs).
Search papers by relevance
PopularTool to search for academic papers by relevance in the Semantic Scholar database. Use when searching for papers on specific topics, keywords, or research areas. Returns papers ordered by relevance score with support for extensive filtering by publication type, date, venue, field of study, and citation metrics.
Details about a paper
Examples: <ul> <li><code>https://api.semanticscholar.org/graph/v1/paper/649def34f8be52c8b66281af98ae884c09aef38b</code></li> <ul> <li>Returns a paper with its paperId and title. </li> </ul> <li><code>https://api.semanticscholar.org/graph/v1/paper/649def34f8be52c8b66281af98ae884c09aef38b?fields=url,year,authors</code></li> <ul> <li>Returns the paper's paperId, url, year, and list of authors. </li> <li>Each author has authorId and name.</li> </ul> <li><code>https://api.semanticscholar.org/graph/v1/paper/649def34f8be52c8b66281af98ae884c09aef38b?fields=citations.authors</code></li> <ul> <li>Returns the paper's paperId and list of citations. </li> <li>Each citation has its paperId plus its list of authors.</li> <li>Each author has their 2 always included fields of authorId and name.</li> </ul> <br> Limitations: <ul> <li>Can only return up to 10 MB of data at a time.</li> </ul> </ul>
Details about a paper s authors
Retrieves the list of authors for a specific paper identified by its unique paper_id in the Semantic Scholar database. This endpoint returns detailed author information including authorId and name (returned by default), and optionally: url, affiliations, homepage, paperCount, citationCount, hIndex, and papers (with subfields). Use the 'fields' parameter to request additional author fields beyond the defaults. The response is paginated and includes offset/limit parameters for retrieving large author lists. This tool is ideal for exploring paper collaborations, identifying author affiliations, or building author networks. It accepts various paper ID formats including Semantic Scholar IDs, DOI, ARXIV, PMID, and others.
Details about a paper s citations
Retrieves a list of citations for a specific academic paper using its unique Semantic Scholar paper ID. This endpoint is useful for researchers and developers who want to explore the impact and connections of a particular academic work within the broader scientific literature. It provides information about other papers that have cited the specified paper, allowing users to trace the influence of research and discover related works. The endpoint should be used when analyzing the reception and impact of a specific paper, building citation networks, or conducting bibliometric studies. It does not provide the full text of citing papers or detailed information about the citations beyond basic metadata.
Details about a paper s references
Retrieves the list of references cited by a specific paper in the Semantic Scholar database. This endpoint allows users to explore the scholarly context of a publication by accessing its bibliography. It's particularly useful for understanding the foundation of a paper's research, tracing the development of ideas, or conducting literature reviews. The tool returns details about the cited papers, which may include their titles, authors, publication dates, and Semantic Scholar IDs. It should be used when analyzing a paper's sources or investigating the connections between different academic works. Note that this endpoint only provides outgoing references (papers cited by the specified paper) and not incoming citations (papers that cite the specified paper).
Details about an author
Retrieve detailed information about an author from Semantic Scholar, including name, affiliations, publication statistics (paperCount, citationCount, h-index), external IDs (ORCID, DBLP), and optionally papers. By default returns authorId and name only. Use 'fields' parameter for additional data: name, url, affiliations, homepage, externalIds, paperCount, citationCount, hIndex, papers (supports nested fields like papers.title, papers.year). Limit: 10 MB per request.
Details about an author s papers
Retrieves a list of papers authored or co-authored by a specific researcher identified by their unique Semantic Scholar author ID. This endpoint is particularly useful for conducting literature reviews, analyzing an author's body of work, or tracking a researcher's publications over time. It provides a comprehensive view of an author's contributions to their field of study, including all papers where the author is listed as an author regardless of their authorship position. The response may be paginated for authors with a large number of publications, and additional API calls might be necessary to retrieve the complete list of papers. Use the offset and limit parameters to control pagination.
Get dataset download links
Tool to get download links for a specific dataset within a release. Use when you need to download Semantic Scholar dataset files from S3. Returns pre-signed URLs for all dataset partitions.
Get dataset diffs
Get download links for incremental diffs between dataset releases. Returns a list of diffs required to update a dataset from start_release to end_release, enabling efficient dataset synchronization. Use when you need to update a local dataset copy without re-downloading the entire dataset.
Show 8 more things it can do
Get details for multiple authors at once
Retrieves detailed information for multiple authors from Semantic Scholar in a single API call. This endpoint allows users to efficiently fetch data for a batch of authors by providing their unique Semantic Scholar IDs. It's particularly useful for applications that need to gather information on multiple authors simultaneously, reducing the number of individual API calls required. The endpoint accepts a list of author IDs and returns comprehensive details for each author, which may include their publications, citations, and other relevant academic information. While the exact response structure is not specified in the given schema, users can expect rich metadata about the requested authors.
Get details for multiple papers at once
Retrieve detailed information for multiple academic papers in a single API call using the Semantic Scholar paper batch endpoint. This endpoint efficiently fetches data for up to 500 papers at once, significantly reducing the number of individual API requests needed. Key features: - Accepts multiple paper ID formats (Semantic Scholar ID, CorpusId, DOI, ArXiv, PMID, etc.) - Customizable field selection to retrieve only needed data - Papers not found return null in the corresponding array position - Results maintain the same order as input IDs - Supports nested field queries (e.g., authors.name, citations.title) Use this endpoint when you have a list of known paper IDs and want to retrieve their details simultaneously, rather than making individual requests for each paper.
Get dataset release information
Tool to retrieve metadata for a specific Semantic Scholar dataset release. Returns release information including available datasets with their descriptions. Use when you need to discover what datasets are available in a release or get release documentation.
List available dataset releases
Tool to list all available dataset releases from Semantic Scholar. Use when you need to discover available release dates for downloading datasets.
Paper title search
Behaves similarly to <code>/paper/search</code>, but is intended for retrieval of a single paper based on closest title match to given query. Examples: <ul> <li><code>https://api.semanticscholar.org/graph/v1/paper/search/match?query=Construction of the Literature Graph in Semantic Scholar</code></li> <ul> <li>Returns a single paper that is the closest title match.</li> <li>Each paper has its paperId, title, and matchScore as well as any other requested fields.</li> </ul> <li><code>https://api.semanticscholar.org/graph/v1/paper/search/match?query=totalGarbageNonsense</code></li> <ul> <li>Returns with a 404 error and a "Title match not found" message.</li> </ul> </ul> <br> Limitations: <ul> <li>Will only return the single highest match result.</li> </ul> </ul>
Search for authors by name
Search for academic authors in the Semantic Scholar database by name. This action searches for authors using plain-text name queries. The search is case-insensitive and supports partial name matches (e.g., "Smith" will match "John Smith", "Adam Smith", etc.). Use cases: - Find authors by their name to get their author ID - Discover authors in a specific research area by searching common names - Retrieve author metadata including publications, affiliations, citation counts, and h-index - Build author directories or research networks The response includes pagination metadata (total, offset, next) to help retrieve large result sets. Use the 'fields' parameter to customize which author attributes are returned, and use 'offset' and 'limit' for pagination through result sets larger than 1000 authors. Note: Results are paginated with a maximum of 1000 results per request. Use the 'next' field in the response to determine the offset for the next page.
Suggest paper query completions
Get autocomplete suggestions for paper queries. Returns a list of papers matching the partial query string, useful for interactive search experiences. Each suggestion includes the paper ID, title, and authors with publication year. Example: For query "machine learning", returns papers like "Machine learning - a probabilistic perspective" by Murphy, 2012.
Text snippet search
Search for text snippets (~500 words) within academic papers that match your natural language query. Returns relevant excerpts from papers' titles, abstracts, and body text, ranked by relevance score. Each result includes: snippet text, location in paper, citation references, and paper metadata (title, authors, corpus ID). Supports filtering by authors, publication date, venue, field of study, citation count, and specific paper IDs. Results sorted by relevance (highest score first). Use limit=10 (default, max 1000) to control result count.
Built for the way you actually work
No code, no engineers
Connect in a few clicks and start using your AI right away. If you can use the apps you already love, you can do this.
Sounds like you, not like a bot
Train your AI on your offer, your voice, and the way you actually talk to clients — it picks up where you leave off.
Plugs into the stack you already use
No need to rip out your CRM, your scheduler, or your email tool. Your AI works inside the apps running your business today.
Your data stays yours
Client conversations, lists, and credentials are scoped to your workspace. Nothing gets shared, sold, or used to train anyone else’s AI.
What you can do once Semantic Scholar is connected
Onboard new clients without lifting a finger
When someone signs up, your AI greets them, sets up their next step in Semantic Scholar, and keeps the momentum going — even at 2am.
Reply to leads in seconds, not days
Your AI watches Semantic Scholar for new inquiries, answers questions in your voice, and books the call before they cool off.
Get your weekends back
Hand off the repetitive Semantic Scholar work — follow-ups, reminders, updates, simple admin — and stop being the bottleneck in your own business.
How to connect Semantic Scholar to your agent
- 1
Start using FormWise for free
Sign up in under a minute.
- 2
Find Semantic Scholar in your connected apps
Inside FormWise, go to Settings → Connected Services and look for Semantic Scholar.
- 3
Hit "Connect"
Click "Connect Semantic Scholar" and log in like you normally would. We only ask for the permissions your AI actually needs.
- 4
Tell your AI what to do in Semantic Scholar
Build a quick AI Agent (it's like writing instructions, not code), and pick the Semantic Scholar actions you want your AI to handle.
- 5
Watch it run
Send it a real-world task and watch your AI take care of Semantic Scholar for you. Tweak the wording until it feels just right.
Powered by the AI you already trust
Your Semantic Scholar workflow runs on the same world-class AI used by ChatGPT, Claude, and Gemini. We handle the technical part — you just tell your AI what to do, in plain English.
- OpenAI
- Anthropic Claude
- Google Gemini
Questions other Semantic Scholar users had before signing up
Do I need to know how to code?
Not even a little. If you can use Semantic Scholar today, you can set this up. You'll connect Semantic Scholar, tell your AI what it should help with, and you're live. The whole thing is built for coaches, course creators, agencies, and operators — not engineers.
Will my clients know they're talking to an AI?
Only if you want them to. Your FormWise AI is trained on your voice, your offer, and the way you actually communicate — so it sounds like a thoughtful team member, not a clunky chatbot. Most people can't tell.
Can I make it sound like me?
Yes. You can give your AI examples of how you write, the questions you usually ask new clients, the way you handle objections, and the language you use about your offer. The more you give it, the more it sounds like you wrote it.
What if I want to take over a conversation?
You're always in control. You can step in at any point, take over from your AI, or stop it from sending messages until you've reviewed them. Think of it as a teammate, not a replacement.
Is my client data safe?
Yes. Your Semantic Scholar login and client information stay scoped to your workspace. We don't sell it, we don't share it, and we don't use your data to train anyone else's AI. You can disconnect Semantic Scholar or delete everything any time.
What happens when Semantic Scholar updates their app?
We handle it. When Semantic Scholar adds new features or changes how something works, we update the integration in the background. You don't have to do anything — your AI just keeps working.
How fast can I actually get this running?
Most people are up and running the same day they sign up. Connecting Semantic Scholar takes a few minutes. Teaching your AI to handle the work the way you'd want it done is the part worth slowing down for.
What is FormWise?
FormWise is the AI agent builder for coaches, course creators, and agencies. You connect the apps you already use — like Semantic Scholar — train your AI on your offer and voice, and let it handle the work you've been doing manually: onboarding, follow-ups, support, admin. No code, no developers, no engineering team required.
Can I sell AI agents to my clients?
Yes. A lot of FormWise users build AI assistants and sell them as part of their offer — done-for-you AI setups, white-label assistants for client businesses, custom GPTs trained on a client's brand. You can charge a setup fee, a monthly retainer, or both.
Can I embed my AI on my website or in my course?
Yes. Every AI you build in FormWise can be embedded on your site, dropped into your course platform, or shared as a standalone link. Your clients and students just open it like any other web page — no app to download, no login hoops.
Do I need to know anything about AI to use this?
No. If you can describe what you want your AI to do in plain English — "greet new clients, ask these 3 questions, book them a call" — FormWise can build it. We handle the models, the prompts, the connections. You handle the part you already know: what your business actually needs.
About Semantic Scholar on FormWise
Semantic Scholar is an AI-powered academic search engine that helps researchers discover and understand scientific literature
Connect Semantic Scholar once and your FormWise AI gets 20 things it can do inside it. That means your AI can handle the Semantic Scholar work in your business — the messages, the updates, the follow-ups, the admin — the way you would, just faster and around the clock.
You don't need to know how any of it works under the hood. We take care of keeping the connection alive, retrying if something fails, and making sure your data only ever moves where you tell it to.
New to Semantic Scholar? Take a look at www.semanticscholar.org.
More artificial intelligence integrations
DataRobot
DataRobot is a machine learning platform that automates model building, deployment, and monitoring, enabling organizations to derive predictive insights from large datasets
OpenWeb Ninja
OpenWeb Ninja provides native APIs for web search, AI answers, e-commerce, finance, jobs, maps, news, real estate, contact enrichment, traffic, and web scraping.
ElevenLabs
Create natural AI voices instantly in any language - perfect for video creators, developers, and businesses.
Griptape
Griptape is a comprehensive platform offering tools and frameworks for building, deploying, and scaling generative AI applications.
Hugging Face
Build, train and deploy state of the art models powered by the reference open source in machine learning.
OpenAI
Toolkit for OpenAI APIs: manage Assistants, Threads/Messages; upload/list/delete Files; list/retrieve Models (including vision/multimodal); and view fine-tune listings and events.
Stop doing the Semantic Scholar work yourself
Hand it off to an AI assistant that sounds like you, works around the clock, and never forgets a follow-up. Free to start.