KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation

2026-09-01

AI Summary

KGVoyager通过动态发现图结构和语义生成SPARQL查询来解决领域特定设置下的知识图谱问答问题，仅需底层图的查询端点。

Abstract

Knowledge Graph Question Answering (KGQA) over RDF graphs remains challenging in domain-specific settings, where formal ontologies and curated text-SPARQL pairs are often unavailable. We present KGVoyager, a KG-agnostic agentic architecture that generates SPARQL queries from natural language questions by dynamically discovering graph structure and semantics, requiring only a query endpoint of the underlying graph. Using a think-act-observe loop with search, exploration, and execution tools, KGVoyager maps terms to graph IRIs, uncovers structure, and refines queries through execution feedback - all without pre-existing ontologies or examples. Unlike the prior state of the art, KGVoyager requires only a lightweight class index which renders it applicable for far more real-world endpoints. Across four benchmarks, KGVoyager improves F1 by ~8 points while cutting cost and runtime by ~22% each.

Problem

• Knowledge Graph Question Answering
• RDF graphs
• domain-specific settings
• formal ontologies
• text-SPARQL pairs

Innovation

• agentic architecture
• dynamic discovery of graph structure
• lightweight class index