用智能代理+知识图谱，让大模型能深度推理复杂科学问题。
Agentic RAG with Knowledge Graphs for Complex Multi-Hop Reasoning in Real-World Applications
- 设计智能代理动态调用知识图谱，实现多跳推理。
- 可精准检索作者全部论文等完整数据集，支持复杂查询。
- 适合科研人员在农业、环境等领域做深度知识探索。
传统检索增强生成（RAG）系统在处理复杂查询时表现有限，常给出片面、提取式答案，难以应对多目标检索或复杂实体关系。本文提出INRAExplorer，一个面向法国国家农业、食品与环境研究院（INRAE）科学数据的智能代理型RAG系统。该系统基于大语言模型构建多工具代理，通过整合公开出版物构建的丰富知识图谱，实现迭代式、精准化查询，支持全量数据检索（如某作者全部论文）、多跳推理，并输出结构化、全面的答案。该系统为专业领域知识交互提供了可落地的范例。
原文摘要 · Abstract (English)
Conventional Retrieval-Augmented Generation (RAG) systems enhance Large Language Models (LLMs) but often fall short on complex queries, delivering limited, extractive answers and struggling with multiple targeted retrievals or navigating intricate entity relationships. This is a critical gap in knowledge-intensive domains. We introduce INRAExplorer, an agentic RAG system for exploring the scientific data of INRAE (France's National Research Institute for Agriculture, Food and Environment). INRAExplorer employs an LLM-based agent with a multi-tool architecture to dynamically engage a rich knowledge base, through a comprehensive knowledge graph derived from open access INRAE publications. This design empowers INRAExplorer to conduct iterative, targeted queries, retrieve exhaustive datasets (e.g., all publications by an author), perform multi-hop reasoning, and deliver structured, comprehensive answers. INRAExplorer serves as a concrete illustration of enhancing knowledge interaction in specialized fields.
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。