让AI医生用自然语言快速查到生命科学文献证据。
EMBL AI Librarian: Life-Sciences Knowledge Layer for AI Agents
- 用大模型规划搜索，自动拆解问题并调用欧洲文献库
- 在 ScholarQABench 上提升 16 点引用准确率，优于现有方法
- 适合生物科研、医药研发中的AI助手使用
随着AI代理越来越多地访问网络，生命科学领域尤其需要高效的知识获取。尽管欧洲文献库（Europe PMC）已收录超过4000万条记录，但其接口不适用于AI代理：需输入关键词和复杂语法，返回整篇论文，导致代理必须学习规则、执行多轮搜索并通读全文才能提取证据。为此，我们提出 EMBL AI Librarian，一个专为AI代理设计的知识层，使代理能以自然语言提问，并直接获得精准的证据答案。该系统由单一大模型协调整个检索流程：规划互补子查询，通过实时欧洲文献库搜索获取结果，再阅读选定论文定位相关证据。我们在四个基准上评估：文献综述、主张验证、开放域问答及下游生物学任务（如实验协议与序列操作）。在 ScholarQABench 上，Librarian 的引用准确率（Citation F1）比最新基线高出16点以上；作为已有主张验证流水线的检索层时，其判断与专家共识一致性提升；在开放型 LitQA2 基准上，使用 GPT-5.4 的代理在引入 Librarian 后得分提高约8分。整体表明，为生命科学代理配备 Librarian 可显著提升多项任务表现。代码已开源：https://github.com/petroni-lab/librarian。
原文摘要 · Abstract (English)
The web is increasingly accessed by AI agents rather than humans. Every agent needs knowledge, especially in the life-sciences, where agentic pipelines are growing fast. Access to the literature is a crucial part of that need, and resources such as Europe PMC, with over 40M indexed records, are widely used to meet it. Yet these resources were not built for AI agents: they take keywords and complex syntax and return whole papers, so every agent must learn the syntax, issue several searches, and read full papers to find the evidence it needs. We introduce EMBL AI Librarian, a knowledge layer that upgrades the Europe PMC interface for AI agents: an agent asks in natural language and receives evidence that answers it. A single LLM orchestrates the whole knowledge retrieval process: it plans complementary subqueries executed by the live Europe PMC search engine, then reads the selected papers and locates the relevant evidence. We evaluate Librarian across four benchmarks: literature synthesis, claim verification, open-domain question answering, and downstream biology tasks such as protocol questions and sequence manipulation. On ScholarQABench, Librarian improves Citation F1 by more than $16$ points over strong recently published baselines. Used as the retrieval layer of an existing claim-verification pipeline, it increases agreement with expert consensus; and on the open-form LitQA2 benchmark, a GPT-5.4 agent scores about $8$ points higher when grounded in Librarian than with web search. Overall, our results show that equipping life-science agents with the Librarian knowledge layer improves performance across a range of tasks. We release our code publicly at https://github.com/petroni-lab/librarian
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。