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

• URL: http://arxiv.org/abs/2510.12831v1
• Date: Sun, 12 Oct 2025 16:12:05 GMT
• Title: MTSQL-R1: Towards Long-Horizon Multi-Turn Text-to-SQL via Agentic Training
• Authors: Taicheng Guo, Hai Wang, ChaoChun Liu, Mohsen Golalikhani, Xin Chen, Xiangliang Zhang, Chandan K. Reddy,
• Abstract summary: We present MT-R1, an agentic training framework for multi-turn Text-to-the-guided.<n>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 verification.<n>Experiments demonstrate that MT-R1 consistently outperforms strong baselines, highlighting the importance of environment-driven verification and memory-guided refinement for conversational semantic parsing.
• Score: 31.290164208264745
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 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.

Related papers

• Monte Carlo Tree Search with Reasoning Path Refinement for Small Language Models in Conversational Text-to-NoSQL [20.156191782890797]
  We introduce the Conversational Text-to-No task, which generates queries given a natural language question, a database, and a dialogue history.<n>We propose Stage-MCTS, a framework that endows small language models with query-specific reasoning capabilities.<n>Our approach outperforms state-of-the-art large reasoning models, improving execution value match accuracy by up to 7.93%.
  arXiv  Detail & Related papers  (2026-02-13T03:35:38Z)
• SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL [20.49395306069103]
  We introduce a multi-turn reinforcement learning (RL) agentic framework for Text-to-one generation.<n>Rather than producing a query in one shot, SQL-Trail interacts with the database environment and uses execution feedback to iteratively refine its predictions.<n>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 incentivizessql correctness and efficient exploration.
  arXiv  Detail & Related papers  (2026-01-25T05:16:52Z)
• Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation [54.53145282349042]
  We introduce DSR-sourced, a textbfDual-textbfS textbfReasoning framework that models Text-to-context as an interaction between an adaptive context state and a progressive generation state.<n>Without any post-training or in-context examples, DSR-sourced achieves competitive performance, reaching 35.28% execution accuracy on Spider 2.0-Snow and 68.32% on BIRD development set.
  arXiv  Detail & Related papers  (2025-11-26T13:52:50Z)
• MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL [22.59453421744114]
  We introduce MARS-, a novel multi-agent framework that combines principled task decomposition and interactive reinforcement learning (RL)<n>Experiments show that MARS- achieves state-of-the-art Execution Accuracy of 77.84% on the BIRD set and 89.84% on the Spider test set.
  arXiv  Detail & Related papers  (2025-11-02T16:55:30Z)
• HI-SQL: Optimizing Text-to-SQL Systems through Dynamic Hint Integration [1.3927943269211591]
  Text-to-generation bridges the gap between natural language and databases, enabling users to query data without requiringsql expertise.<n>We propose HI-the, a pipeline that incorporates a novel hint generation mechanism utilizing historical query logs.<n>By analyzing prior queries, our method generates contextual hints that focus on handling the complexities of multi-table and nested operations.<n>Our approach significantly improves query accuracy of LLM-generated queries while ensuring efficiency in terms of calls and latency.
  arXiv  Detail & Related papers  (2025-06-11T12:07:55Z)
• Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning [0.12289361708127876]
  This work reframes the Text-to-the-task as a pathway for teaching large language models (LLMs) to reason over and manipulate data.<n>We propose a two-stage framework that teaches a model how to traverse, filter, and aggregate table fields.<n> Empirically, our approach achieves substantial gains on reasoning-intensive datasets such as BIRD and CRT-QA.
  arXiv  Detail & Related papers  (2025-04-23T19:02:04Z)
• SQLPrompt: In-Context Text-to-SQL with Minimal Labeled Data [54.69489315952524]
  "Prompt" is designed to improve the few-shot prompting capabilities of Text-to-LLMs. "Prompt" outperforms previous approaches for in-context learning with few labeled data by a large margin. We show that emphPrompt outperforms previous approaches for in-context learning with few labeled data by a large margin.
  arXiv  Detail & Related papers  (2023-11-06T05:24:06Z)
• SQL-PaLM: Improved Large Language Model Adaptation for Text-to-SQL (extended) [53.95151604061761]
  This paper introduces the framework for enhancing Text-to- filtering using large language models (LLMs) With few-shot prompting, we explore the effectiveness of consistency decoding with execution-based error analyses. With instruction fine-tuning, we delve deep in understanding the critical paradigms that influence the performance of tuned LLMs.
  arXiv  Detail & Related papers  (2023-05-26T21:39:05Z)
• MIGA: A Unified Multi-task Generation Framework for Conversational Text-to-SQL [48.34333725045152]
  Most state-of-the-art conversational text-to-generative methods are incompatible with pre-trained language models (PLMs), such as T5. We present a two-stage unified MultI-task Generation frAmeme (MIGA) that leverages PLMs' ability to tackle conversational text-to-work.
  arXiv  Detail & Related papers  (2022-12-19T07:14:32Z)
• STAR: SQL Guided Pre-Training for Context-dependent Text-to-SQL Parsing [64.80483736666123]
  We propose a novel pre-training framework STAR for context-dependent text-to- parsing. In addition, we construct a large-scale context-dependent text-to-the-art conversation corpus to pre-train STAR. Extensive experiments show that STAR achieves new state-of-the-art performance on two downstream benchmarks.
  arXiv  Detail & Related papers  (2022-10-21T11:30:07Z)
• A Survey on Text-to-SQL Parsing: Concepts, Methods, and Future Directions [102.8606542189429]
  The goal of text-to-corpora parsing is to convert a natural language (NL) question to its corresponding structured query language () based on the evidences provided by databases. Deep neural networks have significantly advanced this task by neural generation models, which automatically learn a mapping function from an input NL question to an output query.
  arXiv  Detail & Related papers  (2022-08-29T14:24:13Z)
• Pay More Attention to History: A Context Modeling Strategy for Conversational Text-to-SQL [8.038535788630542]
  One of the most intractable problem of conversational text-to- domain is modeling the semantics of multi-turn queries. This paper shows that explicit modeling the semantic changes by adding each turn and the summarization of the whole context can bring better performance.
  arXiv  Detail & Related papers  (2021-12-16T09:41:04Z)
• Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsing [110.97778888305506]
  BRIDGE represents the question and DB schema in a tagged sequence where a subset of the fields are augmented with cell values mentioned in the question. BRIDGE attained state-of-the-art performance on popular cross-DB text-to- relational benchmarks. Our analysis shows that BRIDGE effectively captures the desired cross-modal dependencies and has the potential to generalize to more text-DB related tasks.
  arXiv  Detail & Related papers  (2020-12-23T12:33:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.