让AI像读文档一样导航结构化信息，精准找证据回答复杂问题。
DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering
- 构建文档层级与跨文档关系的可导航图结构
- 通过动态证据状态提升检索效率，平均准确率提高7.8%
- 适合需要跨文档推理的长文本问答任务
在大型文档集合中回答复杂问题，需整合多章节、多文档中的互补证据。现有GraphRAG通常采用固定遍历路径，而代理型RAG则依赖弱结构接口。我们提出的核心思路是：代理应基于文档内部与跨文档的结构进行导航，而非反复从头搜索。DocNavRAG将文档层次结构与跨区域关系组织为可导航图，提供定位、遍历、扩展和获取等图操作，并维护持续演化的证据状态，指导检索直至收集足够证据。在四个长文本与多文档问答基准上，该方法相比最强基线，平均答案质量提升7.8%，上下文充分性提升17.7%。
原文摘要 · Abstract (English)
Answering complex questions over large document collections requires assembling complementary evidence across sections and documents. GraphRAG offers structured retrieval but typically uses fixed traversal, while agentic RAG operates over weakly structured interfaces. Our key insight is that agents should navigate document structure within and across documents rather than repeatedly search from scratch. We introduce DocNavRAG, which organizes document hierarchies and cross-region relations into a navigable graph, exposes graph operations for locating, navigating, expanding, and fetching, and maintains an evolving evidence state to guide retrieval until sufficient evidence is collected. Across four long- and multi-document QA benchmarks, DocNavRAG improves answer quality and context sufficiency over the strongest baseline by 7.8\% and 17.7\% on average.
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。