对比四种RAG方案，揭示何时该用图谱或智能体增强检索。
Is GraphRAG Needed? From Basic RAG to Graph-/Agentic Solutions with Context Optimization
- 构建统一评估框架，对比常规、图谱、模块化与智能体RAG在9种场景表现。
- 提出新上下文优化方法，减少19%-53%令牌使用，解决记忆溢出问题。
- 发现检索与生成不匹配现象，建议以生成质量而非检索指标评估系统。
随着图谱RAG和智能体RAG等高级变体的出现，一个核心问题是何时以及如何使用它们。本文提出一个针对半结构化知识库的RAG场景评估与比较框架，涵盖常规RAG、图谱RAG、模块化RAG及智能体RAG。我们实现了9个标准化RAG场景，并进行综合实验对比。这些场景覆盖从简单文档检索到混合文本-图谱检索、预定义领域知识图谱集成、多步规划的智能体推理及智能体-图谱融合等真实应用需求。此外，提出一种新型上下文工程方法，通过新表征与智能体循环设计，有效管理文本与图谱检索，实现19%-53%的令牌用量降低。进一步分析揭示‘检索-生成差距’：扩大检索并未成比例提升生成质量，表明以检索为导向的指标高估了先进检索的优势。本研究为构建生产级智能RAG系统提供数据驱动决策依据。
原文摘要 · Abstract (English)
As advanced RAG variants like GraphRAG and Agentic RAG emerge, one leading question is when and how to use them. Here, we introduce a framework for different RAG scenarios evaluation and comparison on semi-structured knowledge bases, including regular RAG, GraphRAG, Modular RAG and Agentic RAG. We provide implementation for 9 standardized RAG scenarios, and conduct experiments for a comprehensive comparison. These scenarios are designed for real use cases regarding data and domain restrictions, spanning from simple document-based retrieval to advanced features such as hybrid text-graph retrieval, integration with computed or pre-defined domain knowledge graphs, agentic multi-step planning, and agent-graph integration. Besides, we present a novel context engineering method for GraphRAG and Agentic RAG, addressing the context/memory overflow issues, efficiently managing text and graph retrievals with new representations and agentic loop design, leading to 19%-53% reduction on token usage. Moreover, further analysis identifies a retrieval-generation gap where expanded retrieval does not proportionally improve generation quality, suggesting retrieval-oriented metrics overstate advanced retrieval benefits. This work provides data-driven insights on when and how to use them for building production-ready intelligent RAG systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。