用结构化链接数据提升智能体检索准确率，效果显著。
Structured Linked Data as a Memory Layer for Agent-Orchestrated Retrieval
- 将知识图谱的结构化数据融入检索系统，增强信息关联性。
- 新格式使标准检索准确率提升29.6%，全链路智能体系统提升29.8%。
- 适合研究智能体推理与知识组织的开发者使用。
现有检索增强生成（RAG）系统通常将文档视为扁平文本，忽视知识图谱提供的结构化元数据与关联关系。本文探究了结构化链接数据（特别是Schema.org标记和可解析的实体页面）在标准与智能体驱动的RAG系统中对检索准确率与回答质量的影响。我们在编辑、法律、旅游、电商四个领域开展受控实验，采用Vertex AI Vector Search 2.0进行检索，Google Agent Development Kit（ADK）实现智能体推理。实验对比七种条件：三种文档表示形式（纯HTML、含JSON-LD的HTML、优化的智能体实体页）与两种检索模式（标准RAG与支持多跳链接遍历的智能体RAG），以及一个增强版（Enhanced+）加入丰富导航功能与实体互链。结果表明，仅使用JSON-LD提升有限；而包含llms.txt式指令、面包屑路径与神经搜索能力的增强实体页，使标准RAG准确率提升29.6%，智能体全流程提升29.8%。Enhanced+版本达最高绝对分（准确率4.85/5，完整性4.55/5），但相较于基础增强版无统计显著增量。研究开源数据集、评估框架与模板以支持复现。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems typically treat documents as flat text, ignoring the structured metadata and linked relationships that knowledge graphs provide. In this paper, we investigate whether structured linked data, specifically Schema.org markup and dereferenceable entity pages served by a Linked Data Platform, can improve retrieval accuracy and answer quality in both standard and agentic RAG systems. We conduct a controlled experiment across four domains (editorial, legal, travel, e-commerce) using Vertex AI Vector Search 2.0 for retrieval and the Google Agent Development Kit (ADK) for agentic reasoning. Our experimental design tests seven conditions: three document representations (plain HTML, HTML with JSON-LD, and an enhanced agentic-optimized entity page) crossed with two retrieval modes (standard RAG and agentic RAG with multi-hop link traversal), plus an Enhanced+ condition that adds rich navigational affordances and entity interlinking. Our results reveal that while JSON-LD markup alone provides only modest improvements, our enhanced entity page format, incorporating llms.txt-style agent instructions, breadcrumbs, and neural search capabilities, achieves substantial gains: +29.6% accuracy improvement for standard RAG and +29.8% for the full agentic pipeline. The Enhanced+ variant, with richer navigational affordances, achieves the highest absolute scores (accuracy: 4.85/5, completeness: 4.55/5), though the incremental gain over the base enhanced format is not statistically significant. We release our dataset, evaluation framework, and enhanced entity page templates to support reproducibility.
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。