mlsanityData to 14 Oct 2026

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

arXiv 2510.12831 ↗First posted 12 Oct 2025cs.CL cs.AI cs.DBcited by 5

On the map: LLM agents and tool use → Web, search, and research agents

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.

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.

Builds on

26 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025WebAgent-R1: Training Web Agents via End-to-End Multi-Turn Reinforcement Learning22 May

Other references · 25

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2024HybridFlow: A Flexible and Efficient RLHF Frameworkcited by 2,057
  3. 2024LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Modelscited by 1,464
  4. 2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
  5. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,210
  6. 2023SGLang: Efficient Execution of Structured Language Model Programscited by 1,141
  7. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  8. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
  9. 2021PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Modelscited by 411
  10. 2022DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scalecited by 407
  11. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  12. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 195
13 more
  1. 2019CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databasescited by 185
  2. 2019SParC: Cross-Domain Semantic Parsing in Contextcited by 144
  3. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 138
  4. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  5. 2019Editing-Based SQL Query Generation for Cross-Domain Context-Dependent Questionscited by 80
  6. 2020Grounded Adaptation for Zero-shot Executable Semantic Parsingcited by 76
  7. 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learningcited by 68
  8. 2023ACT-SQL: In-Context Learning for Text-to-SQL with Automatically-Generated Chain-of-Thoughtcited by 65
  9. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  10. 2020IGSQL: Database Schema Interaction Graph Based Neural Model for Context-Dependent Text-to-SQL Generationcited by 29
  11. 2022HIE-SQL: History Information Enhanced Network for Context-Dependent Text-to-SQL Semantic Parsingcited by 26
  12. 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQLcited by 17
  13. 2024CoE-SQL: In-Context Learning for Multi-Turn Text-to-SQL with Chain-of-Editionscited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 4.

5 papers.

  1. 2025MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQLcited by 15
  2. 2026AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration - Learning from Cheap, Optimizing Expensivecited by 5
  3. 2026SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregationcited by 3
  4. 2026TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemascited by 3
  5. 2026ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experimentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL
  2. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL
  3. 2024R3: "This is My SQL, Are You With Me?" A Consensus-Based Multi-Agent System for Text-to-SQL Tasks
  4. 2025BIRD-INTERACT: Re-imagining Text-to-SQL Evaluation for Large Language Models via Lens of Dynamic Interactions
  5. 2026AgentSM: Semantic Memory for Agentic Text-to-SQL
  6. 2025BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation
  7. 2026Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineering
  8. 2025Continual Learning of Domain Knowledge from Human Feedback in Text-to-SQL