发表机构
School of Computer Science, Wuhan University; The Hong Kong University of Science and Technology; The Chinese University of Hong Kong; ETH Zurich（武汉大学计算机学院; 香港科技大学; 香港中文大学; 苏黎世联邦理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出DocNavRAG，将文档结构组织为可导航图并维护证据状态，在四个文档QA基准上，相比最强基线平均提升答案质量7.8%、上下文充分性17.7%。
AI 中文摘要
针对大型文档集合的复杂问题回答，需要跨章节及文档组装互补证据。GraphRAG提供结构化检索，但通常采用固定遍历；而智能体RAG则在弱结构化接口上运行。本文核心洞见为：智能体应在文档内部及跨文档的结构中导航，而非反复从头搜索。我们提出DocNavRAG，其将文档层级与跨区域关系组织为可导航图，暴露用于定位、导航、扩展及获取的图操作，并维护演化的证据状态以指导检索，直至收集到充足证据。在四个长文档及多文档QA基准上，DocNavRAG相比最强基线，平均提升答案质量7.8%、上下文充分性17.7%。
英文摘要
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.
Comments19 pages, 5 figures, 16 tables
