analiza aiqbench
LivingRAG introduces a writable experience store to graph-based RAG systems, allowing verified reasoning patterns from prior queries to enhance retrieval and answer generation for subsequent related questions. By reusing stored graph signals and summaries, this framework improves accuracy on multi-hop QA benchmarks while reducing the computational cost associated with redundant inference steps. This approach addresses the inefficiency of isolated query processing in current knowledge graph architectures.
LivingRAG: Augmenting Graph RAG with Experience
arXiv:2608.25960v1 Announce Type: new Abstract: 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.
Abstract: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.
Artificial Intelligence (cs.AI)
arXiv:2608.25960 [cs.AI]
(or arXiv:2608.25960v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.25960 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 241 cuvinte
Subiecte conexe
SkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill Graphs
arXiv · 9 oct. 2026
Coordinating from Memory: Graph-Structured Experience Reuse for Multi-Agent Adaptation in Dynamic Manufacturing
arXiv · 23 iul. 2026
Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge
arXiv · 3 sept. 2026
Fast State-Augmented Learning for Wireless Resource Allocation with Dual Variable Regression
arXiv · 27 iul. 2026