KGVoyager: Knowledge Graph Agnostic Question Answering via Agentic Navigation
Essam Wisam, Chengkai Li
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.
Create a lesson
Related papers
Incremental Pooled LLM Evaluation for Cost-Effective Retrieval Model Selection
Max Nelson, Hanoz Bhathena, Aviral Joshi et al.
Recommender System as Slow and Fast Thinkers
Zichen Yuan, Xiaoxuan Dong, Linkun Dai et al.
Training seeds and model-selection stability in recommender-system evaluation
Juan Manuel Rodriguez, Oleg Lesota, Antonela Tommasel
ViSAR: Training-Free Adaptive-k Retrieval for Visual Document Question Answering
Adrien Mialland, Marc Plantevit, Julien Gallois et al.
Adaptive Test-Time Inference for Text2Cypher with Trace Budgeting and Selective Refinement
Makbule Gulcin Ozsoy
Counter-GEO-Bench: Evaluating Defenses Against Information-Distorting Generative Engine Optimization
Bing Zheng, Zongyao Zhao, Wenming Yang