Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems

• URL: http://arxiv.org/abs/2604.09666v1
• Date: Wed, 01 Apr 2026 07:21:32 GMT
• Title: Do We Still Need GraphRAG? Benchmarking RAG and GraphRAG for Agentic Search Systems
• Abstract summary: Retrieval-augmented generation (RAG) and its graph-based extensions (GraphRAG) are effective paradigms for improving large language model (LLM) reasoning.<n>Recent agentic search systems enable dynamic, multi-round retrieval and sequential decision-making during inference.<n>We introduce RAGSearch, a unified benchmark that evaluates dense RAG and representative GraphRAG methods as retrieval infrastructures under agentic search.
• Score: 9.226583502132753
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Retrieval-augmented generation (RAG) and its graph-based extensions (GraphRAG) are effective paradigms for improving large language model (LLM) reasoning by grounding generation in external knowledge. However, most existing RAG and GraphRAG systems operate under static or one-shot retrieval, where a fixed set of documents is provided to the LLM in a single pass. In contrast, recent agentic search systems enable dynamic, multi-round retrieval and sequential decision-making during inference, and have shown strong gains when combined with vanilla RAG by introducing implicit structure through interaction. This progress raises a fundamental question: can agentic search compensate for the absence of explicit graph structure, reducing the need for costly GraphRAG pipelines? To answer this question, we introduce RAGSearch, a unified benchmark that evaluates dense RAG and representative GraphRAG methods as retrieval infrastructures under agentic search. RAGSearch covers both training-free and training-based agentic inference across multiple question answering benchmarks. To ensure fair and reproducible comparison, we standardize the LLM backbone, retrieval budgets, and inference protocols, and report results on full test sets. Beyond answer accuracy, we report offline preprocessing cost, online inference efficiency, and stability. Our results show that agentic search substantially improves dense RAG and narrows the performance gap to GraphRAG, particularly in RL-based settings. Nevertheless, GraphRAG remains advantageous for complex multi-hop reasoning, exhibiting more stable agentic search behavior when its offline cost is amortized. Together, these findings clarify the complementary roles of explicit graph structure and agentic search, and provide practical guidance on retrieval design for modern agentic RAG systems.

Related papers

• Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization [9.99981815735792]
  We introduce a framework for different RAG scenarios evaluation and comparison on semi-structured knowledge bases.<n>We provide implementation for 9 standardized RAG scenarios, and conduct experiments for a comprehensive comparison.
  arXiv  Detail & Related papers  (2026-06-24T10:11:02Z)
• Use Graph When It Needs: Efficiently and Adaptively Integrating Retrieval-Augmented Generation with Graphs [12.14017207383674]
  Large language models (LLMs) often struggle with knowledge-intensive tasks due to hallucinations and outdated parametric knowledge.<n>Retrieval-Augmented Generation (RAG) addresses this by integrating external corpora, but its effectiveness is limited by fragmented information in unstructured domain documents.<n>GraphRAG emerged to enhance contextual reasoning through structured knowledge graphs, yet paradoxically underperforms vanilla RAG in real-world scenarios.<n>We propose EA-GraphRAG that dynamically integrates RAG and GraphRAG paradigms through syntax-aware complexity analysis.
  arXiv  Detail & Related papers  (2026-02-03T14:26:28Z)
• Query-Efficient Agentic Graph Extraction Attacks on GraphRAG Systems [29.89127594311822]
  Graph-based retrieval-augmented generation (GraphRAG) systems construct knowledge graphs over document collections to support multi-hop reasoning.<n>We study a budget-constrained black-box setting where an adversary adaptively queries the system to steal its latent entity-relation graph.<n>We propose AGEA, a framework that leverages a novelty-guided exploration-exploitation strategy, external graph memory modules, and a two-stage graph extraction pipeline.
  arXiv  Detail & Related papers  (2026-01-21T05:20:54Z)
• RouteRAG: Efficient Retrieval-Augmented Generation from Text and Graph via Reinforcement Learning [69.87510139069218]
  Retrieval-Augmented Generation (RAG) integrates non-parametric knowledge into Large Language Models (LLMs)<n>Recent progress has advanced text-based RAG to multi-turn reasoning through Reinforcement Learning (RL)<n>We introduce model, an RL-based framework that enables LLMs to perform multi-turn and adaptive graph-text hybrid RAG.
  arXiv  Detail & Related papers  (2025-12-10T10:05:31Z)
• LinearRAG: Linear Graph Retrieval Augmented Generation on Large-scale Corpora [17.929144506419064]
  Retrieval-Augmented Generation (RAG) is widely used to mitigate hallucinations of Large Language Models (LLMs) by leveraging external knowledge.<n>Existing graph-based RAG methods rely on unstable and costly relation extraction for graph construction.<n>We propose LinearRAG, an efficient framework that enables reliable graph construction and precise passage retrieval.
  arXiv  Detail & Related papers  (2025-10-11T08:43:45Z)
• GRIL: Knowledge Graph Retrieval-Integrated Learning with Large Language Models [59.72897499248909]
  We propose a novel graph retriever trained end-to-end with Large Language Models (LLMs)<n>Within the extracted subgraph, structural knowledge and semantic features are encoded via soft tokens and the verbalized graph, respectively, which are infused into the LLM together.<n>Our approach consistently achieves state-of-the-art performance, validating the strength of joint graph-LLM optimization for complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-09-20T02:38:00Z)
• Graph-R1: Towards Agentic GraphRAG Framework via End-to-end Reinforcement Learning [20.05893083101089]
  Graph-R1 is an agentic GraphRAG framework via end-to-end reinforcement learning (RL)<n>It introduces lightweight knowledge hypergraph construction, models retrieval as a multi-turn agent-environment interaction.<n>Experiments on standard RAG datasets show that Graph-R1 outperforms traditional GraphRAG and RL-enhanced RAG methods in reasoning accuracy, retrieval efficiency, and generation quality.
  arXiv  Detail & Related papers  (2025-07-29T15:01:26Z)
• Divide by Question, Conquer by Agent: SPLIT-RAG with Question-Driven Graph Partitioning [62.640169289390535]
  SPLIT-RAG is a multi-agent RAG framework that addresses the limitations with question-driven semantic graph partitioning and collaborative subgraph retrieval.<n>The innovative framework first create Semantic Partitioning of Linked Information, then use the Type-Specialized knowledge base to achieve Multi-Agent RAG.<n>The attribute-aware graph segmentation manages to divide knowledge graphs into semantically coherent subgraphs, ensuring subgraphs align with different query types.<n>A hierarchical merging module resolves inconsistencies across subgraph-derived answers through logical verifications.
  arXiv  Detail & Related papers  (2025-05-20T06:44:34Z)
• RGL: A Graph-Centric, Modular Framework for Efficient Retrieval-Augmented Generation on Graphs [58.10503898336799]
  We introduce the RAG-on-Graphs Library (RGL), a modular framework that seamlessly integrates the complete RAG pipeline.<n>RGL addresses key challenges by supporting a variety of graph formats and integrating optimized implementations for essential components.<n>Our evaluations demonstrate that RGL not only accelerates the prototyping process but also enhances the performance and applicability of graph-based RAG systems.
  arXiv  Detail & Related papers  (2025-03-25T03:21:48Z)
• RAG vs. GraphRAG: A Systematic Evaluation and Key Insights [53.83444096699458]
  We systematically evaluate Retrieval-Augmented Generation (RAG) and GraphRAG on text-based benchmarks.<n>Our results highlight the distinct strengths of RAG and GraphRAG across different tasks and evaluation perspectives.
  arXiv  Detail & Related papers  (2025-02-17T02:36:30Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.