KGVoyager is presented, 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.
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.
PYTHIA is presented, a training-free, plug-and-play solution for KGQA over any RDF KG which consists of an LLM agent guided by a relation-centric conceptual model of the KGQA task which is acted upon through a suite of tools for entity linking, graph exploration and query execution.
Sergios-Anestis Kefalidis, Konstantinos Plas, Manolis Koubarakis· Proceedings of the 32nd ACM...· 1 citation
We present EXYGEN (EXplore Your Graphs ENgine), a framework for knowledge graph (KG) understanding that enables conversational access to KGs at scale. We address two questions in sequence. First, how effectively can LLMs perform text-to-SPARQL generation given only automatically derived structured metadata and small gr...
Harshdeep Singh, Yu-Rui Zhu, Giovanni Colavizza et al.· 0 citations
This work presents an agentic text-to-SPARQL system that goes one step beyond static tool-using agents: a researcher agent that, after each round of inference on a validation set, proposes and tests changes to its own prompts, rules, and tool-orchestration code.
To bridge the semantic gap in NL2SQL (Natural Language to SQL) tasks, this study proposes a "Question→SQL→Wiki" framework that leverages a dynamic Wiki Graph as an intermediate reasoning layer. Departing from conventional NL2SQL approaches that rely solely on end-to-end mapping, our method utilizes Large Language Model...
Jia-Xuan Liu, Shi-Yu Fang, Ji-Bing Wu et al.· 2026 12th International Conf...· 0 citations
This work proposes KGCache, an in-memory cache for one-hop knowledge graph neighborhoods, which is designed to be compatible with both iterative traversal (ToG) and one shot planning (RoG) KGQA paradigms and shows substantial entity reuse among starting entities and entities reached during traversal.
Uros Stanic, Chang-He Yuan, Sabuj Laskar et al.· 0 citations
GRA is presented, a Graph Reasoning Agent that explores hybrid knowledge graphs, whose nodes are either textual concepts or relational tables, with seven generic tools, discovering everything domain-specific at run time.
M. Dragić, Ruben Ifrah, Alexandre Rio· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
