---
title: "LivingRAG：为图 RAG 注入可复用推理经验"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.25960v1"
permalink: "https://feed.astralor.com/items/itm_b7cde3531fdf1d9e285e2fb5"
published: "2026-08-26T16:21:06.000Z"
score: 70
channel: "ai"
tags: ["LivingRAG","图检索增强生成","检索增强生成","知识图谱","经验复用"]
---

# LivingRAG：为图 RAG 注入可复用推理经验

## AI 点评

> 这篇论文把 RAG 从一次性的孤立查询变成可持续积累经验的系统，对做知识密集型和多跳问答的团队特别有启发。真实业务里很多问题是重复且关联的，与其每次从头检索，不如把已验证的推理沉淀成可复用资产，这可能是降低成本的关键。

## 速览

LivingRAG 提出一种可写可复用的经验库，为图检索增强生成（Graph RAG）增加经验存储。它将已验证的推理结果拆分为图信号与摘要两类：图信号在后续相关查询中辅助召回实体和段落，摘要则提供答案生成的参考推理模式。在线问答流中的共享实体、图邻域和问题模板可产生可复用信号，在多跳问答基准上提升了准确率，并减少补全 token 的使用。

## 关键点

- LivingRAG 在 Graph RAG 检索主干上增加可写入的经验库，使推理经验能在后续查询中复用。
- 经验以图信号和摘要两种形式存储，分别作用于检索阶段和答案生成阶段。
- 从共享实体、图邻域和问题模板中提取可复用信号，缓解多跳问答中重复检索与推理的问题。
- 多跳问答实验显示，该框架相较强 RAG 基线提升准确率并降低补全 token 消耗。

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_b7cde3531fdf1d9e285e2fb5