Query-Centric Graph Retrieval Augmented Generation
On the map: LLM reasoning → Knowledge- and tool-augmented reasoning
Abstract (arXiv)
Graph-based retrieval-augmented generation (RAG) enriches large language models (LLMs) with external knowledge for long-context understanding and multi-hop reasoning, but existing methods face a granularity dilemma: fine-grained entity-level graphs incur high token costs and lose context, while coarse document-level graphs fail to capture nuanced relations. We introduce QCG-RAG, a query-centric graph RAG framework that enables query-granular indexing and multi-hop chunk retrieval. Our query-centric approach leverages Doc2Query and Doc2Query{-}{-} to construct query-centric graphs with controllable granularity, improving graph quality and interpretability. A tailored multi-hop retrieval mechanism then selects relevant chunks via the generated queries. Experiments on LiHuaWorld and MultiHop-RAG show that QCG-RAG consistently outperforms prior chunk-based and graph-based RAG methods in question answering accuracy, establishing a new paradigm for multi-hop reasoning.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 22 of its 38 references that are in the map. First posted on arXiv 25 Sep 2025.
Builds on
22 of 38 references.
Closest ancestors · 1
Same direction, newest first
Other references · 21
- 2023GPT-4 Technical Reportcited by 18,396
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
- 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
- 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
- 2024A Survey on LLM-as-a-Judgecited by 1,423
- 2024Graph Retrieval-Augmented Generation: A Surveycited by 324
- 2024LightRAG: Simple and Fast Retrieval-Augmented Generationcited by 315
- 2024MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queriescited by 257
- 2019Document Expansion by Query Predictioncited by 231
9 more
- 2024Retrieval-Augmented Generation with Graphs (GraphRAG)cited by 172
- 2024Evaluation of Retrieval-Augmented Generation: A Surveycited by 146
- 2025A Survey of Graph Retrieval-Augmented Generation for Customized Large Language Modelscited by 88
- 2025MiniRAG: Towards Extremely Simple Retrieval-Augmented Generationcited by 28
- 2023Doc2Query--: When Less is Morecited by 21
- 2024KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Modelscited by 12
- 2025Towards Practical GraphRAG: Efficient Knowledge Graph Construction and Hybrid Retrieval at Scalecited by 9
- 2025Hierarchical Lexical Graph for Enhanced Multi-Hop Retrievalcited by 7
- 2024Mixture-of-PageRanks: Replacing Long-Context with Real-Time, Sparse GraphRAGcited by 2
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2025Clue-RAG: Towards Accurate and Cost-Efficient Graph-based RAG via Multi-Partite Graph and Query-Driven Iterative Retrieval
- 2025Beyond Static Retrieval: Opportunities and Pitfalls of Iterative Retrieval in GraphRAG
- 2025NodeRAG: Structuring Graph-based RAG with Heterogeneous Nodes
- 2026Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs
- 2025Graph-based Approaches and Functionalities in Retrieval-Augmented Generation: A Comprehensive Survey
- 2026Reasoning in Trees: Improving Retrieval-Augmented Generation for Multi-Hop Question Answering
- 2025In-depth Analysis of Graph-based RAG in a Unified Framework
- 2026DA-RAG: Dynamic Attributed Community Search for Retrieval-Augmented Generation