Apr 23, 2026 · cs.AIJ/K move · Enter open · S save
Qiang Gao, Zhenping Li, Anqi Zhuo, Yingxiao Zhao+2
Center of Information Research, Academy of Military Science, Beijing 100142, China · School of Mathematics and Physics, University of Science and Technology Beijing, Beijing 100083, China
Existing text-to-SQL synthesis pipelines still conflate executability with semantic validity: syntactic checks and execution-based validation can retain queries that execute successfully while violating database semantics. To address these limitations, we propose SemanticAgent, a semantic-aware synthesis framework. SemanticAgent organizes synthesis around three specialized modules: an analyzer, a synthesizer, and a verifier. Through a three-stage protocol of semantic analysis, stepwise synthesis, and diagnostic refinement, SemanticAgent transforms execution-based validation alone into a traceable reasoning process. Our framework generates synthetic data that consistently outperforms prior synthesis methods under semantic-quality evaluation, leading to stronger downstream fine-tuning performance, especially on semantically demanding benchmarks.