Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2509.22009 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916978896142336 |
|---|---|
| author | Yang, Cehao Wu, Xiaojun Lin, Xueyuan Xu, Chengjin Jiang, Xuhui Sun, Yuanliang Li, Jia Xiong, Hui Guo, Jian |
| author_facet | Yang, Cehao Wu, Xiaojun Lin, Xueyuan Xu, Chengjin Jiang, Xuhui Sun, Yuanliang Li, Jia Xiong, Hui Guo, Jian |
| contents | 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 \textsc{GraphSearch}, a novel agentic deep searching workflow with dual-channel retrieval for GraphRAG. \textsc{GraphSearch} organizes the retrieval process into a modular framework comprising six modules, enabling multi-turn interactions and iterative reasoning. Furthermore, \textsc{GraphSearch} 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 \textsc{GraphSearch} consistently improves answer accuracy and generation quality over the traditional strategy, confirming \textsc{GraphSearch} as a promising direction for advancing graph retrieval-augmented generation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_22009 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation Yang, Cehao Wu, Xiaojun Lin, Xueyuan Xu, Chengjin Jiang, Xuhui Sun, Yuanliang Li, Jia Xiong, Hui Guo, Jian Computation and Language 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 \textsc{GraphSearch}, a novel agentic deep searching workflow with dual-channel retrieval for GraphRAG. \textsc{GraphSearch} organizes the retrieval process into a modular framework comprising six modules, enabling multi-turn interactions and iterative reasoning. Furthermore, \textsc{GraphSearch} 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 \textsc{GraphSearch} consistently improves answer accuracy and generation quality over the traditional strategy, confirming \textsc{GraphSearch} as a promising direction for advancing graph retrieval-augmented generation. |
| title | GraphSearch: An Agentic Deep Searching Workflow for Graph Retrieval-Augmented Generation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2509.22009 |