SAGA: Schema-Aware Grounding for Agentic Text-to-SPARQL Generation

Jul 17, 2026

SAGA is a training-free framework designed to improve agentic text-to-SPARQL generation by systematically incorporating schema constraints. By maintaining a bidirectional type state and filtering out incompatible property candidates, SAGA reduces the search space and prevents semantically invalid queries. The framework achieves the highest F1 scores across all nine benchmark settings on Wikidata and Freebase, and the highest exact-match accuracy on eight of them, while also reducing empty-result queries.

Why it matters: This work systematically addresses type-blind grounding in interactive KBQA agents, leading to more accurate and efficient SPARQL query generation.

Full story at: arXiv AI/ML ↗