mlsanityData to 14 Oct 2026

GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation

arXiv 2509.22009 ↗First posted 26 Sep 2025cs.CLcited by 3

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

also in 2 more
Abstract (arXiv)

Graph Retrieval-Augmented Generation (GraphRAG) enhances factual reasoning in LLMs by structurally modeling knowledge through graph-based representations. However, existing GraphRAG approaches face two core limitations: shallow retrieval that fails to surface all critical evidence, and inefficient utilization of pre-constructed structural graph data, which hinders effective reasoning from complex queries. To address these challenges, we propose textscGraphSearch, a novel agentic deep searching workflow with dual-channel retrieval for GraphRAG. textscGraphSearch organizes the retrieval process into a modular framework comprising six modules, enabling multi-turn interactions and iterative reasoning. Furthermore, textscGraphSearch adopts a dual-channel retrieval strategy that issues semantic queries over chunk-based text data and relational queries over structural graph data, enabling comprehensive utilization of both modalities and their complementary strengths. Experimental results across six multi-hop RAG benchmarks demonstrate that textscGraphSearch consistently improves answer accuracy and generation quality over the traditional strategy, confirming textscGraphSearch as a promising direction for advancing graph retrieval-augmented generation.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 40 of its 43 references that are in the map. First posted on arXiv 26 Sep 2025.

Builds on

40 of 43 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning12 Mar
  2. 2025Search-o1: Agentic Search-Enhanced Large Reasoning Models9 Jan
  3. 2024Plan*RAG: Efficient Test-Time Planning for Retrieval Augmented Generation28 Oct
  4. 2024Think-on-Graph 2.0: Deep and Faithful Large Language Model Reasoning with Knowledge-guided Retrieval Augmented Generation15 Jul

Other references · 36

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  3. 2018HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answeringcited by 3,754
  4. 2023Qwen Technical Reportcited by 3,344
  5. 2023A Survey of Large Language Modelscited by 2,576
  6. 2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
  7. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  8. 2024A Survey on LLM-as-a-Judgecited by 1,423
  9. 2020Constructing A Multi-hop QA Dataset for Comprehensive Evaluation of Reasoning Stepscited by 1,282
  10. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  11. 2023Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Modelscited by 698
  12. 2023A Comprehensive Overview of Large Language Modelscited by 648
24 more
  1. 2024RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrievalcited by 532
  2. 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
  3. 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
  4. 2023RECOMP: Improving Retrieval-Augmented LMs with Compression and Selective Augmentationcited by 256
  5. 2025From RAG to Memory: Non-Parametric Continual Learning for Large Language Modelscited by 231
  6. 2023Query Rewriting for Retrieval-Augmented Large Language Modelscited by 213
  7. 2023Survey on Factuality in Large Language Models: Knowledge, Retrieval and Domain-Specificitycited by 206
  8. 2024FlashRAG: A Modular Toolkit for Efficient Retrieval-Augmented Generation Researchcited by 166
  9. 2024RQ-RAG: Learning to Refine Queries for Retrieval Augmented Generationcited by 147
  10. 2024MemoRAG: Boosting Long Context Processing with Global Memory-Enhanced Retrieval Augmentationcited by 119
  11. 2025HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representationcited by 68
  12. 2025PathRAG: Pruning Graph-based Retrieval Augmented Generation with Relational Pathscited by 61
  13. 2024Modular RAG: Transforming RAG Systems into LEGO-like Reconfigurable Frameworkscited by 42
  14. 2024Small Models, Big Insights: Leveraging Slim Proxy Models To Decide When and What to Retrieve for LLMscited by 34
  15. 2024HybGRAG: Hybrid Retrieval-Augmented Generation on Textual and Relational Knowledge Basescited by 29
  16. 2025MiniRAG: Towards Extremely Simple Retrieval-Augmented Generationcited by 28
  17. 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodescited by 26
  18. 2025Hyper-RAG: Combating LLM Hallucinations using Hypergraph-Driven Retrieval-Augmented Generationcited by 23
  19. 2025PropRAG: Guiding Retrieval with Beam Search over Proposition Pathscited by 23
  20. 2024GeAR: Graph-enhanced Agent for Retrieval-augmented Generationcited by 17
  21. 2025LongFaith: Enhancing Long-Context Reasoning in LLMs with Faithful Synthetic Datacited by 16
  22. 2025CausalRAG: Integrating Causal Graphs into Retrieval-Augmented Generationcited by 12
  23. 2025ComposeRAG: A Modular and Composable RAG for Corpus-Grounded Multi-Hop Question Answeringcited by 11
  24. 2023A Step Closer to Comprehensive Answers: Constrained Multi-Stage Question Decomposition with Large Language Modelscited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 3.

3 papers.

  1. 2026S-Path-RAG: Semantic-Aware Shortest-Path Retrieval Augmented Generation for Multi-Hop Knowledge Graph Question Answeringcited by 3
  2. 2026LARGER: Lexically Anchored Repository Graph Exploration and Retrievalcited by 2
  3. 2026Integrating Graphs, Large Language Models, and Agents: Reasoning and Retrievalcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026GraphSearch: Agentic Search-Augmented Reasoning for Zero-Shot Graph Learning
  2. 2026Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems
  3. 2026A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning
  4. 2026GraphScout: Empowering Large Language Models with Intrinsic Exploration Ability for Agentic Graph Reasoning
  5. 2025Youtu-GraphRAG: Vertically Unified Agents for Graph Retrieval-Augmented Complex Reasoning
  6. 2025Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs
  7. 2026GRASP: Graph Agentic Search over Propositions for Multi-hop Question Answering
  8. 2024LEGO-GraphRAG: Modularizing Graph-based Retrieval-Augmented Generation for Design Space Exploration