Retrieval-Augmented Generation (RAG) has significantly enhanced Large Language Models' ability to access external knowledge, yet current graph-based RAG approaches face two critical limitations in managing hierarchical information: they impose rigid layer-specific compression quotas that damage local graph structures, and they prioritize topological structure while neglecting semantic content. We introduce T-Retriever, a novel framework that reformulates attributed graph retrieval as tree-based retrieval using a semantic and structure-guided encoding tree. Our approach features two key innovations: (1) Adaptive Compression Encoding, which replaces artificial compression quotas with a global optimization strategy that preserves the graph's natural hierarchical organization, and (2) Semantic-Structural Entropy ($S^2$-Entropy), which jointly optimizes for both structural cohesion and semantic consistency when creating hierarchical partitions. Experiments across diverse graph reasoning benchmarks demonstrate that T-Retriever significantly outperforms state-of-the-art RAG methods, providing more coherent and contextually relevant responses to complex queries.

翻译：检索增强生成显著提升了大型语言模型访问外部知识的能力，然而当前基于图的检索增强生成方法在处理层次化信息时面临两个关键局限：它们施加了僵化的层特定压缩配额，破坏了局部图结构；并且优先考虑拓扑结构而忽视了语义内容。我们提出了T-Retriever，一种新颖的框架，它利用语义与结构引导的编码树，将属性图检索重新表述为基于树的检索。我们的方法具有两个关键创新：(1) 自适应压缩编码，它用全局优化策略取代人工压缩配额，以保留图的自然层次化组织；(2) 语义-结构熵，它在创建层次化划分时，联合优化结构内聚性与语义一致性。在多样化的图推理基准测试上的实验表明，T-Retriever显著优于当前最先进的检索增强生成方法，能为复杂查询提供更连贯且上下文更相关的响应。