Graph-based Retrieval-Augmented Generation (GraphRAG) frameworks face a trade-off between the comprehensiveness of global search and the efficiency of local search. Existing methods are often challenged by navigating large-scale hierarchical graphs, optimizing retrieval paths, and balancing exploration-exploitation dynamics, frequently lacking robust multi-stage re-ranking. To overcome these deficits, we propose Deep GraphRAG, a framework designed for a balanced approach to hierarchical retrieval and adaptive integration. It introduces a hierarchical global-to-local retrieval strategy that integrates macroscopic inter-community and microscopic intra-community contextual relations. This strategy employs a three-stage process: (1) inter-community filtering, which prunes the search space using local context; (2) community-level refinement, which prioritizes relevant subgraphs via entity-interaction analysis; and (3) entity-level fine-grained search within target communities. A beam search-optimized dynamic re-ranking module guides this process, continuously filtering candidates to balance efficiency and global comprehensiveness. Deep GraphRAG also features a Knowledge Integration Module leveraging a compact LLM, trained with Dynamic Weighting Reward GRPO (DW-GRPO). This novel reinforcement learning approach dynamically adjusts reward weights to balance three key objectives: relevance, faithfulness, and conciseness. This training enables compact models (1.5B) to approach the performance of large models (70B) in the integration task. Evaluations on Natural Questions and HotpotQA demonstrate that Deep GraphRAG significantly outperforms baseline graph retrieval methods in both accuracy and efficiency.

翻译：基于图的检索增强生成（GraphRAG）框架面临着全局搜索的全面性与局部搜索的效率之间的权衡。现有方法在导航大规模分层图结构、优化检索路径以及平衡探索-利用动态性方面常面临挑战，且通常缺乏鲁棒的多阶段重排序机制。为克服这些不足，本文提出深度图检索增强生成（Deep GraphRAG）框架，旨在实现分层检索与自适应融合的平衡。该框架引入了一种从全局到局部的分层检索策略，整合了宏观的社区间与微观的社区内上下文关系。该策略采用三阶段流程：（1）社区间过滤，利用局部上下文对搜索空间进行剪枝；（2）社区级精化，通过实体交互分析对相关子图进行优先级排序；（3）在目标社区内进行实体级细粒度搜索。一个基于束搜索优化的动态重排序模块引导此过程，持续筛选候选结果以平衡效率与全局覆盖性。Deep GraphRAG 还配备了一个知识融合模块，该模块利用经动态加权奖励 GRPO（DW-GRPO）训练的紧凑型大语言模型。这种新颖的强化学习方法动态调整奖励权重，以平衡三个关键目标：相关性、忠实性与简洁性。该训练使得紧凑模型（1.5B 参数）在融合任务中能够接近大型模型（70B 参数）的性能。在 Natural Questions 和 HotpotQA 数据集上的评估表明，Deep GraphRAG 在准确性与效率上均显著优于基线图检索方法。