作者位次 #3/10ACL 2026Poster· Natural Language Processing
R e E x- SQL : Reasoning with Execution-Aware Reinforcement Learning for Text-to- SQL
Yaxun Dai · Wenxuan Xie · Xialie Zhuang · Tianyu Yang · Ziyi Liu · Haiqin Yang · Yiying Yang · Yuhang Zhao · Pingfu Chao · Wenhao Jiang
摘要
Current Text-to-SQL reasoning models often lack integrated execution feedback during generation, and most existing approaches utilize feedback only for post-hoc correction. This separation not only limits real-time error correction, but may also introduce mistakes by altering otherwise correct SQ...