Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Taicheng Guo, Hai Wang, ChaoChun Liu, Mohsen Golalikhani, Xin Chen, Xiangliang Zhang, Chandan K. Reddy• 2025

Related benchmarks

TaskDatasetResultRank
Text-to-SQLSpider
Exec Acc (All)84.2
139
Multi-turn Text-to-SQLCoSQL In-domain
Exact Match65.2
29
Multi-turn Text-to-SQLCoSQL & SParC Aggregate
Avg Exact Match (EM)66.5
29
Multi-turn Text-to-SQLSParC In-domain
Exact Match68.7
29
Text-to-SQLBird
Execution Accuracy56.9
20
Multi-turn Text-to-SQLCoSQL Out-of-domain
Execution Accuracy74
16
Multi-turn Text-to-SQLSParC Out-of-domain
Execution Accuracy (EX)77.4
16
Showing 7 of 7 rows

Other info

Follow for update