@inproceedings{guo-etal-2026-mtsql,
    title = "{MTSQL}-R1: Towards Long-Horizon Multi-Turn Text-to-{SQL} via Agentic Training",
    author = "Guo, Taicheng  and
      Wang, Hai  and
      Liu, Chaochun  and
      Golalikhani, Mohsen  and
      Chen, Xin  and
      Zhang, Xiangliang  and
      Reddy, Chandan K.",
    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.1563/",
    pages = "33905--33938",
    ISBN = "979-8-89176-390-6",
    abstract = "Multi-turn Text-to-SQL aims to translate a user{'}s conversational utterances into executable SQL while preserving dialogue coherence and grounding to the target schema. However, most existing systems only regard this task as a simple text translation task and follow a short-horizon paradigm, generating a query per turn without execution, explicit verification, and refinement, which leads to non-executable or incoherent outputs. We present MTSQL-R1, an agentic training framework for long-horizon multi-turn Text-to-SQL. We cast the task as a Markov Decision Process (MDP) in which an agent interacts with (i) a database for execution feedback and (ii) a persistent dialogue memory for coherence verification, performing an iterative propose-{\ensuremath{>}}execute-{\ensuremath{>}}verify-{\ensuremath{>}}refine cycle until all checks pass. Experiments on CoSQL and SParC demonstrate that MTSQL-R1 consistently outperforms strong baselines, highlighting the importance of environment-driven verification and memory-guided refinement for conversational semantic parsing. Full recipes (including code, trained models, reasoning trajectories, etc.) will be released upon acceptance to contribute to community research."
}