# MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training

arXiv: https://arxiv.org/abs/2510.12831 · HTML: https://mlsanity.com/paper/2510.12831/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 12 Oct 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 26 of 26)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learning](https://mlsanity.com/paper/2503.09516/) (2025)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task](https://mlsanity.com/paper/1809.08887/) (2018)
- [RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parsers](https://mlsanity.com/paper/1911.04942/) (2019)
- [PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models](https://mlsanity.com/paper/2109.05093/) (2021)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluation](https://mlsanity.com/paper/2308.15363/) (2023)
- [RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQL](https://mlsanity.com/paper/2302.05965/) (2023)
- [CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases](https://mlsanity.com/paper/1909.05378/) (2019)
- [WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning](https://mlsanity.com/paper/2505.16421/) (2025)
- [SParC: Cross-Domain Semantic Parsing in Context](https://mlsanity.com/paper/1906.02285/) (2019)
- [CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQL](https://mlsanity.com/paper/2410.01943/) (2024)
- [RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL](https://mlsanity.com/paper/2205.06983/) (2022)
- [Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questions](https://mlsanity.com/paper/1909.00786/) (2019)
- [Grounded Adaptation for Zero-shot Executable Semantic Parsing](https://mlsanity.com/paper/2009.07396/) (2020)
- [SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning](https://mlsanity.com/paper/2504.08600/) (2025)
- [ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thought](https://mlsanity.com/paper/2310.17342/) (2023)
- [Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL](https://mlsanity.com/paper/2503.23157/) (2025)
- [IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generation](https://mlsanity.com/paper/2011.05744/) (2020)
- [HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsing](https://mlsanity.com/paper/2203.07376/) (2022)
- [STaR-SQL: Self-Taught Reasoner for Text-to-SQL](https://mlsanity.com/paper/2502.13550/) (2025)
- [CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editions](https://mlsanity.com/paper/2405.02712/) (2024)

## Built on by (most cited first, 5 of 5)

- [MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL](https://mlsanity.com/paper/2511.01008/) (2025)
- [AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensive](https://mlsanity.com/paper/2605.11518/) (2026)
- [SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregation](https://mlsanity.com/paper/2603.16161/) (2026)
- [TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas](https://mlsanity.com/paper/2603.16448/) (2026)
- [ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments](https://mlsanity.com/paper/2606.25207/) (2026)

## Abstract (arXiv)

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 to execute -> verify -> 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, logs, reasoning trajectories, etc.) will be released after the internal review to contribute to community research.