KGVoyager：基于智能体导航的知识图无关问答
KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation
浏览论文内容
中文总结 AI 辅助
KGVoyager是一种知识图无关的智能体问答架构，仅需轻量级类索引即可从自然语言生成SPARQL查询，在四个基准测试中F1提升约8个百分点，成本与运行时间各降约22%。
中文摘要 AI 辅助
针对RDF图的知识图问答（KGQA）在特定领域场景中仍具挑战性，这类场景往往缺少形式化本体和精心整理的文本-SPARQL对。我们提出KGVoyager，一种知识图无关的智能体架构，仅需底层图的查询端点，即可通过动态发现图结构与语义，从自然语言问题生成SPARQL查询。KGVoyager采用“思考-行动-观察”循环，结合搜索、探索、执行工具，将术语映射到图IRI、揭示结构并通过执行反馈优化查询，全程无需预存本体或示例。与现有最优方法不同，KGVoyager仅需轻量级类索引，使其适用于更多真实世界端点。在四个基准测试中，KGVoyager的F1值提升约8个百分点，同时成本和运行时间各降低约22%。
英文摘要
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.
发表机构
- University of Texas at Arlington（阿灵顿得克萨斯大学）
机构由 AI 辅助整理，请以论文原文为准。
