DocNavRAG: Document-Structured Graph RAG with Stateful Evidence Construction for Complex Document Question Answering

arXiv:2608.01565v1 Announce Type: new 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.

Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering
When More Documents Hurt RAG: Mitigating Vector Search Dilution with Domain-Scoped, Model-Agnostic Retrieval
HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Document
Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization

Source: arXiv cs.CL | 2026-08-04

Related