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

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 $\text{textsc}GraphSearch$, a novel agentic deep searching workflow with dual-channel retrieval for GraphRAG. $\text{textsc}GraphSearch$ organizes the retrieval process into a modular framework comprising six modules, enabling multi-turn interactions and iterative reasoning. Furthermore, $\text{textsc}GraphSearch$ 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 $\text{textsc}GraphSearch$ consistently improves answer accuracy and generation quality over the traditional strategy, confirming $\text{textsc}GraphSearch$ as a promising direction for advancing graph retrieval-augmented generation.