@inproceedings{sterbentz-etal-2026-mixed,
    title = "Mixed-Policy {GRPO} for Text-to-{SQL} with Off-Policy Data Generation",
    author = "Sterbentz, Marko  and
      Glass, Michael  and
      Pham, Nhan H  and
      Subramanian, Dharmashankar  and
      Hammond, Kristian J",
    editor = "Gupta, Vivek  and
      Ding, Kaize  and
      Kokel, Harsha  and
      Zhao, Yue  and
      Agarwal, Amit  and
      Wang, Yu  and
      Glass, Michael  and
      Zhang, Yu  and
      Srinivas, Kavitha  and
      Chen, Xiusi  and
      Hassanzadeh, Oktie  and
      Zhu, Qi  and
      Chang, Shuaichen  and
      Luo, Yuan",
    booktitle = "Proceedings of the First Workshop on Structured Understanding, Retrieval, and Generation in the {LLM} Era ({SURG}e{LLM} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.surgellm-1.20/",
    pages = "313--325",
    ISBN = "979-8-89176-406-4",
    abstract = "Recent advances in text-to-SQL have shown that methods such as Group Relative Policy Optimization (GRPO) can substantially improve reasoning performance, but these approaches remain inherently on-policy, limiting their ability to incorporate novel reasoning patterns. In this work, we address this limitation by leveraging existing datasets to generate high-quality off-policy rollouts, enabling mixed-policy training that exposes models to diverse and informative reasoning trajectories. We present the first application of mixed-policy GRPO to the text-to-SQL domain and introduce a systematic study of off-policy data generation strategies for this setting, including a novel method, Iterative Error Correction (IEC), which iteratively refines model outputs through targeted feedback. Our experiments show that mixed-policy GRPO outperforms both base models and on-policy GRPO, yielding average improvements of +4.7{\%} over base models and +4.1{\%} over on-policy GRPO across the Spider and BIRD benchmarks. Gains are particularly strong on BIRD, reaching up to +7.3{\%} over base models and +4.5{\%} over on-policy GRPO."
}