Search papers, labs, and topics across Lattice.
This paper introduces LivingRAG, a novel framework that enhances graph-based retrieval-augmented generation (RAG) by incorporating a writable experience store to facilitate the reuse of reasoning across related queries. By leveraging stored graph signals and summaries, LivingRAG enables more efficient retrieval and answer generation, significantly improving performance on multi-hop question answering tasks. Experimental results demonstrate that LivingRAG outperforms traditional RAG systems in accuracy and reduces token usage by effectively reusing relevant prior experiences.
Reusing reasoning from previous queries can boost multi-hop QA accuracy while cutting down on token usage, transforming how we approach graph-based retrieval systems.
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 retrieval find entities and passages that were useful in earlier related queries. Stored summaries provide a reference reasoning pattern for answer generation. We analyze online QA streams and find reusable signals from shared entities, graph neighborhoods, and question templates. Experiments on multi-hop QA benchmarks show that LivingRAG improves accuracy over strong RAG baselines and reduces completion-token use when relevant prior experience is reused.
