mlsanityData to 7 Oct 2026

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

arXiv 2608.01565 ↗First posted 3 Aug 2026cs.CLcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 17 of its 30 references that are in the map. First posted on arXiv 3 Aug 2026.

Builds on

17 of 30 references.

References · 17

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  4. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  5. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  6. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  7. 2024LongBench v2: Towards Deeper Understanding and Reasoning on Realistic Long-context Multitaskscited by 367
  8. 2024Graph Retrieval-Augmented Generation: A Surveycited by 320
  9. 2024GRAG: Graph Retrieval-Augmented Generationcited by 77
  10. 2024Sufficient Context: A New Lens on Retrieval Augmented Generation Systemscited by 69
  11. 2025Retrieval-Augmented Generation with Hierarchical Knowledgecited by 46
  12. 2024PlanRAG: A Plan-then-Retrieval Augmented Generation for Generative Large Language Models as Decision Makerscited by 42
5 more
  1. 2024M3SciQA: A Multi-Modal Multi-Document Scientific QA Benchmark for Evaluating Foundation Modelscited by 26
  2. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodescited by 25
  3. 2026A-RAG: Scaling Agentic Retrieval-Augmented Generation via Hierarchical Retrieval Interfacescited by 24
  4. 2025Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generationcited by 23
  5. 2025Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challengescited by 19

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Trace Only What You Need: Structure-Aware On-Demand Hypergraph Memory for Long-Document Question Answering
  2. 2026HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Document
  3. 2026PAGE-RAG: Evidence-Grounded Adaptive Graph Retrieval for Long-Document Question Answering
  4. 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
  5. 2026VecTree-RAG: An Agentic Retrieval-Augmented Generation Framework Combining Vector and Tree Retrieval for Efficiency and Accuracy
  6. 2026DocTrace: Towards Traceable Long Document VQA via Hierarchical Evidence Graph Reasoning
  7. 2026SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation
  8. 2026G2-Reader: Dual Evolving Graphs for Multimodal Document QA