Preprint
Aug 2026
SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning
This work proposes SERL-SQL, a selective execution-grounded reinforcement learning framework for multi-turn Text-to-SQL agents, showing that SERL-SQL produces high-quality candidates that can be reliably identified by lightweight execution-grounded rewards.
Tao Liu, Tao Feng, Xiangheng Li et al.
· 0 citations