SOURCE-LINKED INTELLIGENCE

LivingRAG: Augmenting Graph RAG with Experience

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Graph-based RAG improves multi-hop question answering by organizing evidence as a knowledge graph. However, most existing RAG systems process each query in isolation and discard useful reasoning from the LLM's response after inference. As a result, later related queries need to retrieve evidence and reason from scratch. We propose LivingRAG, a Graph RAG framework with writable and reusable reasoning experience. LivingRAG adds a writable experience store to a graph-based retrieval backbone, enabling verified experiences to be reused during inference in two ways. Stored graph signals help retrie

Read original source ↗ Open in workspace

recordType

paper

region

Global