Back to Details

firecrawl-research-index

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

firecrawl research

firecrawl research

Find the papers that answer a research query. When in doubt, return the relevant set (most relevant first) rather than one hit.
查找能回答研究问题的论文。若不确定，返回相关论文集（按相关性从高到低排序）而非单篇论文。

Quick start

快速开始

bash
mkdir -p .firecrawl
firecrawl research search-papers "CRISPR base editing off-target effects" \
  --limit 20 -o .firecrawl/papers.json --json
jq -r '.results[] | .primaryId, .title' .firecrawl/papers.json
Run 
firecrawl research <subcommand> --help
for flags. MCP arguments use 
paperId
, not 
id
.
A successful 
search-papers
response is 
{success, results}
. Each hit carries 
paperId
, 
primaryId
(
pmid:
, 
pmcid:
, 
doi:
, or 
arxiv:
), 
ids
, 
title
, 
abstract
, and 
score
.
Done when: the answer is a cited paper set (or the one named paper), each kept or dropped against a verified constraint, with 
search-papers
as the first move unless the query already named an id.
bash
mkdir -p .firecrawl
firecrawl research search-papers "CRISPR base editing off-target effects" \
  --limit 20 -o .firecrawl/papers.json --json
jq -r '.results[] | .primaryId, .title' .firecrawl/papers.json
运行 
firecrawl research <subcommand> --help
查看可用参数。MCP 参数使用 
paperId
，而非 
id
。
search-papers
命令执行成功后会返回 
{success, results}
。每条结果包含 
paperId
、
primaryId
（格式为
pmid:
、
pmcid:
、
doi:
或
arxiv:
）、
ids
、
title
、
abstract
和
score
。
完成标志： 答案为经过验证筛选后的引用论文集（或指定的单篇论文），除非查询已指定论文ID，否则第一步需执行
search-papers
命令。

Tips

技巧

  • search-papers
    is the first move. If results look thin or all-alike, re-run with a different framing (sibling domain, rival method, dataset/benchmark name).
  • related-papers
    needs 
    --intent
    . 
    mode=similar
    for siblings, 
    citers
    for who builds on the seeds, 
    references
    for what they build on.
  • inspect-paper
    is metadata for one id. 
    read-paper
    is in-body passages for one constraint (sample size, method, affiliation). Use it to rule a paper out, not to gatekeep.
  • search --categories research
    is a website filter. It returns pages from academic domains, not paper records in this index.
  • Named paper ("the Qwen3 report") → one 
    search-papers
    . Method / family / "papers that do X" → expand with 
    related-papers
    and keep neighbors.
  • Superlative / leaderboard questions live on the web: 
    firecrawl search
    / 
    firecrawl scrape
    , then 
    search-papers
    each top entry.
  • PubMed, bioRxiv, and medRxiv are the largest part of the corpus. Do not send a biomedical query to the open web on the assumption the index is arXiv-only.
  • 第一步执行
    search-papers
    。若结果数量少或同质化严重，更换查询框架（如相关领域、替代方法、数据集/基准名称）重新运行。
  • related-papers
    命令需要指定
    --intent
    参数。
    mode=similar
    用于查找相似论文，
    citers
    用于查找引用该论文的文献，
    references
    用于查找该论文引用的文献。
  • inspect-paper
    用于查询单篇论文的元数据。
    read-paper
    用于提取单篇论文中符合特定约束条件的内容片段（如样本量、研究方法、机构归属）。该命令用于排除不符合要求的论文，而非作为准入门槛。
  • search --categories research
    是网站过滤器，返回学术领域的网页，而非本索引中的论文记录。
  • 若查询指定论文（如“the Qwen3 report”），执行一次
    search-papers
    即可。若查询方法/系列/“做X的论文”，则需使用
    related-papers
    扩展结果并筛选相关论文。
  • 关于最优结果/排行榜的问题需通过网页检索：先执行
    firecrawl search
    /
    firecrawl scrape
    ，再对每个顶级条目执行
    search-papers
    。
  • PubMed、bioRxiv和medRxiv是语料库中占比最大的部分。请勿假设本索引仅包含arXiv内容，将生物医学查询发送至开放网页检索。

See also

另请参阅

  • firecrawl-search — web pages, including 
    search --categories research
  • firecrawl-scrape — leaderboards and other non-paper pages
  • firecrawl-developer-index — issues, PRs, READMEs, and docs
  • firecrawl-search — 网页检索，包括
    search --categories research
    功能
  • firecrawl-scrape — 抓取排行榜及其他非论文类网页
  • firecrawl-developer-index — 检索问题、PR、README及文档