Query and Conquer: Execution-Guided SQL Generation

We propose a novel approach for generating complex outputs that significantly improves accuracy in text-to-SQL tasks. Our method leverages execution results to select the most semantically consistent query from multiple candidates, enabling smaller, cost-effective models to surpass computationally intensive reasoning methods such as o1, o3-mini, and DeepSeek R1 while reducing inference cost by as much as 30 times. It integrates effortlessly with existing models, offering a practical and scalable pathway to state-of-the-art SQL generation.

@article{borchmann2025_2503.24364,
  title={ Query and Conquer: Execution-Guided SQL Generation },
  author={ Łukasz Borchmann and Marek Wydmuch },
  journal={arXiv preprint arXiv:2503.24364},
  year={ 2025 }
}