MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQL

Zekun Xu, Siyu Xia, Chuhuai Yue, Jiajun Chai, Mingxue Tian, Xiaohan Wang, Wei Lin, Haoxuan Li, Guojun Yin

Track: long paper (up to 10 pages)

Keywords: Text-to-SQL、Multi-turn Tool-Integrated Reasoning、Reinforcement Learning

TL;DR: MTIR-SQL: A reinforcement learning framework that enhances Text-to-SQL through multi-turn reasoning with real-time database feedback integration.

Abstract: As large language models (LLMs) are increasingly used in Text-to-SQL tasks, Reinforcement Learning (RL) has become a common method for improving performance. Existing methods primarily rely on static execution feedback, which restricts real-time error correction. However, integrating multi-turn tool invocation along with dynamic feedback could significantly improve adaptability and robustness, ultimately enhancing model performance. To address these issues, we propose MTIR-SQL, an innovative Multi-turn Tool-Integrated Reasoning reinforcement learning framework for Text-to-SQL. Our approach introduces an execution-aware multi-turn reasoning paradigm that seamlessly incorporates database execution feedback at each reasoning step, enabling context-sensitive query generation and progressive refinement throughout the reasoning process. The framework extends the GRPO algorithm to accommodate complex multi-turn interaction scenarios. Considering the training instability characteristics of MTIR and the potential for significant Deviation of model distribution from the initial model, we enhance the GRPO algorithm by adding a trajectory filtering mechanism and removing KL loss constraints. Experimental results show that MTIR-SQL achieves 64.4\% and 84.6\% execution accuracy on BIRD and SPIDER Dev sets with a compact 4B-parameter backbone, yielding a significant 16\% absolute gain over baseline and even surpassing larger-scale models like DeepSeek-V3.

Presenter: ~Zekun_Xu5

Format: Maybe: the presenting author will attend in person, contingent on other factors that still need to be determined (e.g., visa, funding).

Anonymization: This submission has been anonymized for double-blind review via the removal of identifying information such as names, affiliations, and identifying URLs.

Funding: No, the presenting author of this submission does *not* fall under ICLR’s funding aims, or has sufficient alternate funding.

Submission Number: 60