SOURCE-LINKED INTELLIGENCE

SQL-Zero: Self-Evolving Text-to-SQL

arXiv · AI, language, vision and robotics · article · Sep 4, 2026 · UTC

Training a competitive Text-to-SQL agent usually depends on human-annotated natural-language/SQL pairs, which are expensive, domain-specific, and a bottleneck for scaling to new databases. We show it is possible to train a competitive solver with zero annotated pairs. We introduce SQL-Zero, a proposer-solver self-play in which a challenger and a solver start from the same base LLM and the only ground truth is execution against the database itself. The challenger generates SQL pairs calibrated to the solver's current difficulty (targeting "hard but solvable"), and both roles are updated with GR

Read original source ↗ Open in workspace

recordType

paper

region

Global