DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learning
This work proposes DualSQL, a new Text-to-SQL system consisting of two agents powered by a single model backbone, enabling joint optimization through a robust multi-agent reinforcement learning (RL) framework, and introduces a new SQL correctness metric, robust execution match (REX), to more accurately judge SQL correc...
Shi-Jie Chen, Yu Gan, Yeounoh Chung et al.
· 0 citations