两篇新研究论文LiteRAG和CAGE提出了改进检索增强生成（RAG）系统的新颖方法。LiteRAG通过使用算法探索而非昂贵的LLM控制来专注于降低查询时间成本和提高生成效率，在基准测试中实现了高质量，同时显著降低了延迟和成本。CAGE引入了一个重新排序框架，该框架模拟检索到的段落之间的连贯性，将它们转换为图，并使用关系图卷积网络来增强事实一致性并提高下游答案的精确度。
AI
arXiv:2609.10239v1 Announce Type: cross Abstract: Graph-based retrieval can improve multi-hop question answering, but existing approaches often incur high query-time costs and produce diffuse, oversized contexts that reduce generation efficiency. We present LiteRAG, a graph-based…
Graph-based retrieval can improve multi-hop question answering, but existing approaches often incur high query-time costs and produce diffuse, oversized contexts that reduce generation efficiency. We present LiteRAG, a graph-based retrieval method that replaces expensive retrieva…
arXiv:2609.04647v1 Announce Type: new Abstract: Traditional Retrieval-Augmented Generation (RAG) systems score each passage independently against the query, assembling context sets that may be individually relevant yet collectively incoherent. We introduce Coherence-Aware Graph E…
Traditional Retrieval-Augmented Generation (RAG) systems score each passage independently against the query, assembling context sets that may be individually relevant yet collectively incoherent. We introduce Coherence-Aware Graph Encoding (CAGE), a reranking framework that model…
<h1> GraphRAG in 2026: When Vector Search Stops Being Enough </h1> <p>In April 2024, Microsoft Research published "From Local to Global: A Graph RAG Approach to Query-Focused Summarization" (Edge, Trinh, Cheng, Bradley, Chao, Mody, Truitt, Metropolitansky, Ness, & Larson; arX…
