mlsanityData to 7 Oct 2026

Hierarchical Abstract Tree for Cross-Document Retrieval-Augmented Generation

arXiv 2605.00529 ↗First posted 1 May 2026cs.LG cs.AI cs.IRcited by 0

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Retrieval-augmented generation (RAG) enhances large language models with external knowledge, and tree-based RAG organizes documents into hierarchical indexes to support queries at multiple granularities. However, existing Tree-RAG methods designed for single-document retrieval face critical challenges in scaling to cross-document multi-hop questions: (1) poor distribution adaptability, where k-means clustering introduces noise due to rigid distribution assumptions; (2) structural isolation, as tree indexes lack explicit cross-document connections; and (3) coarse abstraction, which obscures fine-grained details. To address these limitations, we propose Psi-RAG, a tree-RAG framework with two key components. First, a hierarchical abstract tree index built through an iterative "merging and collapse" process that adapts to data distributions without a priori assumption. Second, a multi-granular retrieval agent that intelligently interacts with the knowledge base with reorganized queries and an agent-powered hybrid retriever. Psi-RAG supports diverse tasks from token-level question answering to document-level summarization. On cross-document multi-hop QA benchmarks, it outperforms RAPTOR by 25.9% and HippoRAG 2 by 7.4% in average F1 score. Code is available at https://github.com/Newiz430/Psi-RAG.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 53 of its 76 references that are in the map. First posted on arXiv 1 May 2026.

Builds on

53 of 76 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025GraphRAG-Bench: Challenging Domain-Specific Reasoning for Evaluating Graph Retrieval-Augmented Generation3 Jun
  2. 2025Retrieval-Augmented Generation with Hierarchical Knowledge13 Mar
  3. 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Paths18 Feb
  4. 2025ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation14 Feb
  5. 2024Simple Is Effective: The Roles of Graphs and Large Language Models in Knowledge-Graph-Based Retrieval-Augmented Generation28 Oct
  6. 2024Graph of Records: Boosting Retrieval Augmented Generation for Long-context Summarization with Graphs14 Oct
  7. 2024LightRAG: Simple and Fast Retrieval-Augmented Generation8 Oct
  8. 2024Hierarchical Retrieval-Augmented Generation Model with Rethink for Multi-hop Question Answering20 Aug
  9. 2024Graph Retrieval-Augmented Generation: A Survey15 Aug
  10. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarization24 Apr
  11. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval31 Jan

Other references · 42

  1. 2024The Llama 3 Herd of Modelscited by 14,192
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  4. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  5. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,779
  6. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,686
  7. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  8. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,800
  9. 2025Gemma 3 Technical Reportcited by 1,686
  10. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,259
  11. 2021Unsupervised Dense Information Retrieval with Contrastive Learningcited by 1,203
  12. 2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,175
30 more
  1. 2020ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERTcited by 1,160
  2. 2022When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memoriescited by 1,103
  3. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  4. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 893
  5. 2016Efficient and robust approximate nearest neighbor search using Hierarchical Navigable Small World graphscited by 853
  6. 2017The NarrativeQA Reading Comprehension Challengecited by 590
  7. 2024NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Modelscited by 466
  8. 2024A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Modelscited by 450
  9. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Modelscited by 423
  10. 2024The Faiss librarycited by 370
  11. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 363
  12. 2024∞Bench: Extending Long Context Evaluation Beyond 100K Tokenscited by 360
  13. 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 253
  14. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 223
  15. 2025When More is Less: Understanding Chain-of-Thought Length in LLMscited by 182
  16. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 165
  17. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 122
  18. 2023Dense X Retrieval: What Retrieval Granularity Should We Use?cited by 88
  19. 2024BM25S: Orders of magnitude faster lexical search via eager sparse scoringcited by 87
  20. 2024From Isolated Conversations to Hierarchical Schemas: Dynamic Tree Memory Representation for LLMscited by 77
  21. 2020A Large-Scale Multi-Document Summarization Dataset from the Wikipedia Current Events Portalcited by 72
  22. 2020From Trees to Continuous Embeddings and Back: Hyperbolic Hierarchical Clusteringcited by 65
  23. 2015A cost function for similarity-based hierarchical clusteringcited by 63
  24. 2022The Hidden Uniform Cluster Prior in Self-Supervised Learningcited by 57
  25. 2025Towards Agentic RAG with Deep Reasoning: A Survey of RAG-Reasoning Systems in LLMscited by 40
  26. 2021Dense Hierarchical Retrieval for Open-Domain Question Answeringcited by 33
  27. 2016Approximate Hierarchical Clustering via Sparsest Cut and Spreading Metricscited by 26
  28. 2024T-RAG: Lessons from the LLM Trenchescited by 23
  29. 2025Hierarchical Document Refinement for Long-context Retrieval-augmented Generationcited by 16
  30. 2025LLM-guided Hierarchical Search for End-to-end Reasoning Intensive Retrievalcited by 4

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SPD-RAG: Sub-Agent Per Document Retrieval-Augmented Generation
  2. 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
  3. 2025BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents
  4. 2025Hierarchical Lexical Graph for Enhanced Multi-Hop Retrieval
  5. 2026Bridge-RAG: An Abstract Bridge Tree Based Retrieval Augmented Generation Algorithm
  6. 2026A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
  7. 2025Optimizing Multi-Hop Document Retrieval Through Intermediate Representations
  8. 2026UnWeaving the knots of GraphRAG -- turns out VectorRAG is almost enough