---
title: "Selective Retrieval Routing for Multi-Violation Knowledge Graph Repair"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.07342v1"
permalink: "https://feed.astralor.com/items/itm_fa7657f76dfee275b5f61b10"
published: "2026-11-05T02:29:58.000Z"
score: 57
channel: "tech"
tags: ["LLM","AI Agent","RAG","多模态","Selective Retrieval Routing","Multi-Violation Knowledge Graph","Repair Knowledge","Schema"]
---

# Selective Retrieval Routing for Multi-Violation Knowledge Graph Repair

## At a glance

Knowledge graphs often contain missing or inconsistent facts that undermine the applications built on them. Schema validation detects such violations but does not identify which of several valid repairs recovers the int…

## Key points

- Knowledge graphs often contain missing or inconsistent facts that undermine the applications built on them.
- Schema validation detects such violations but does not identify which of several valid repairs recovers the intended graph.
- External corpora can supply the evidence needed to identify the intended repair, but retrieving from them is costly and not always successful.

## Full text

Knowledge graphs often contain missing or inconsistent facts that undermine the applications built on them. Schema validation detects such violations but does not identify which of several valid repairs recovers the intended graph. External corpora can supply the evidence needed to identify the intended repair, but retrieving from them is costly and not always successful. We propose a framework for selective retrieval in iterative graph repair. An LLM repair agent explores and edits the graph, while a router controls its access to a researcher agent that retrieves external evidence. We extend a violation-injection framework to generate cases with multiple compatible violations and known reference repairs. The agent's repair outcomes on these cases provide supervision for training the deployment-specific router. On two building-automation datasets, researcher access improves repairs for some violations and degrades them for others, with effects differing across deployments. The router uses fewer repair-time tokens than always enabling access in all six evaluation suites. It achieves higher repair $F_1$ than always disabling access in five of six suites.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_fa7657f76dfee275b5f61b10