# DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering Source: [DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering]() Collection index: [llms.txt]() Data updated: 2026-08-05T05:00:12.726Z Authors: Dongyang Xie, Yao Tian, Hao Zhang, Yifei Yuan, Tieyun Qian, Ming Zhong, Jiawei Jiang, Yuanyuan Zhu (1) \_\_INSTITUTION\_8\_\_ School of Computer Science, Wuhan University, (2) The Hong Kong University of Science, Technology, (3) The Chinese University of Hong Kong, (4) ETH Zurich) Published: 2026-08-03T00:48:05.000Z ## Abstract 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. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. ## Original sources and implementation [Original paper]() [PDF]()