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

arXiv:2510.12831v3 Announce Type: replace 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

• Knapsack Optimization-based Schema Linking for LLM-based Text-to-SQL Generation
• Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
• FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents
• ODUTQA-MDC: A Task for Open-Domain Underspecified Tabular QA with Multi-turn Dialogue-based Clarification
• Agentic Jackal: Live Execution and Semantic Value Grounding for Text-to-JQL

Source: arXiv cs.CL | 2026-04-21