Firecrawl Research Search Papers
Search for research papers across indexed areas including AI/ML, computer science, mathematics, physics, biomedical and life sciences, and clinical literature. Provide a natural-language research topic or question as `query`. You may request `k` ranked papers (1–500; default 40), filter by `authors` (all supplied case-insensitive author substrings must match) or `categories` (all supplied values must match), and set inclusive `from` and `to` bounds for created or updated dates using `YYYY-MM-DD`. The synchronous response contains a ranked `results` array; paper records may include `paperId`, `primaryId`, source `ids`, title, authors, abstract, categories, and created/update dates. Optional `agent_hints` may be included. Try several distinct formulations of a topic for broader recall. This is a search operation, not an asynchronous task workflow.
Pricing
| Condition | Charge |
|---|---|
| Each call | 0 credits/call |
Each paper search call has a fixed charge of 0 credits.
Parameters
Optional parameters use the platform defaults when omitted.
| Parameter | Type | Required | Description | Default |
|---|---|---|---|---|
k | integer | No | Number of ranked papers to return (default 40). | — |
to | string | No | Inclusive upper bound on created/updated date (`YYYY-MM-DD`). | — |
from | string | No | Inclusive lower bound on created/updated date (`YYYY-MM-DD`). | — |
query | string | Yes | Natural-language research topic or question, including methods, systems, conditions, populations, interventions, or outcomes when relevant. | — |
authors | array | No | Author substring filter(s); ALL must match (case-insensitive). | — |
categories | array | No | Paper category filter(s) (e.g. `cs.LG`); ALL provided values must match. | — |
Invocation example
Copy the request and explore its response example.
/agent-api/v1/tool/executeX-Api-Keycurl --request POST \
--url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_firecrawl_research_search_papers' \
--header "X-Api-Key: $AGENTEARTH_API_KEY" \
--header 'Content-Type: application/json' \
--data-raw '{
"params": {
"k": 9,
"query": "Stock prediction large language models benchmark multimodal numerical textual FinTSB MASTER 2024 2025 2026",
"to": "2026-11-11"
}
}'"## [arxiv:2606.24950] MacroLens: A Multi-Task Benchmark for Contextual Financial Reasoning under Macroeconomic Scenarios\nAuthors: Patara Trirat; Jin Myung Kwak; Jay Heo; Heejun Lee; Sung Ju Hwang\nDates: created 2026-06-23; updated 2026-06-25\nFinancial deci"This example shows part of the response. Copied content is valid JSON.
Guides using this tool
See how this tool fits into real workflows

