@inproceedings{hua-etal-2026-sql,
    title = "{SQL}-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-{SQL}",
    author = "Hua, Harper  and
      Han, Zhen  and
      Shen, Zhengyuan  and
      Lee, Meng-Chieh  and
      Guan, Sheng  and
      Zhu, Qi  and
      Jeoung, Sullam  and
      Chen, Yueyan  and
      Bai, Yunfei  and
      Wang, Shuai  and
      Ioannidis, Vassilis N.  and
      Rangwala, Huzefa",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1677/",
    pages = "36224--36246",
    ISBN = "979-8-89176-390-6",
    abstract = "While large language models (LLMs) have substantially improved Text-to-SQL generation, a pronounced gap remains between AI systems and human experts on challenging benchmarks such as BIRD-SQL. We argue this gap stems largely from the prevailing single-pass paradigm, which lacks the iterative reasoning, schema exploration, and error-correction behaviors that humans naturally employ. To address this limitation, we introduce SQL-Trail, a multi-turn reinforcement learning (RL) agentic framework for Text-to-SQL. Rather than producing a query in one shot, SQL-Trail interacts with the database environment and uses execution feedback to iteratively refine its predictions. Our approach centers on two key ideas: (i) an adaptive turn-budget allocation mechanism that scales the agent{'}s interaction depth to match question difficulty, and (ii) a composite reward panel that jointly incentivizes SQL correctness and efficient exploration. Across benchmarks, SQL-Trail sets a new state of the art and delivers strong data efficiency{---}up to **18{\texttimes}** higher than prior single-pass RL state-of-the-art methods. Notably, our 7B and 14B models outperform substantially larger proprietary systems by **5{\%}** on average, underscoring the effectiveness of interactive, agentic workflows for robust Text-to-SQL generation."
}