TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas

• URL: http://arxiv.org/abs/2603.16448v2
• Date: Wed, 18 Mar 2026 03:45:57 GMT
• Title: TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemas
• Abstract summary: We propose TRUST- (Truthful Reasoning with Unknown via Tools)<n>We formulate the task as a Partially Observable Markov Decision Process where our autonomous agent employs a structured four-phase protocol to ground reasoning in verified.<n>By applying token-level masked advantages, this strategy isolates exploration rewards from execution outcomes to resolve credit assignment.
• Score: 22.65474240295148
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Text-to-SQL parsing has achieved remarkable progress under the Full Schema Assumption. However, this premise fails in real-world enterprise environments where databases contain hundreds of tables with massive noisy metadata. Rather than injecting the full schema upfront, an agent must actively identify and verify only the relevant subset, giving rise to the Unknown Schema scenario we study in this work. To address this, we propose TRUST-SQL (Truthful Reasoning with Unknown Schema via Tools). We formulate the task as a Partially Observable Markov Decision Process where our autonomous agent employs a structured four-phase protocol to ground reasoning in verified metadata. Crucially, this protocol provides a structural boundary for our novel Dual-Track GRPO strategy. By applying token-level masked advantages, this strategy isolates exploration rewards from execution outcomes to resolve credit assignment, yielding a 9.9% relative improvement over standard GRPO. Extensive experiments across five benchmarks demonstrate that TRUST-SQL achieves an average absolute improvement of 30.6% and 16.6% for the 4B and 8B variants respectively over their base models. Remarkably, despite operating entirely without pre-loaded metadata, our framework consistently matches or surpasses strong baselines that rely on schema prefilling.

Related papers

• Spider 2.0-AIFunc: Extending Real-World Text-to-SQL to AI-Native SQL Workflows [54.49251107006261]
  We introduce Spider 2.0-AIFunc, a benchmark of 465 verified instances across 125 real-world databases covering six types of AI functions on the Snowflake platform.<n>We find that the strongest proprietary models reach 67-70% execution accuracy while the best open-source model achieves 58.1%.
  arXiv  Detail & Related papers  (2026-07-07T12:54:08Z)
• ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQL [51.98164069124653]
  ProSPy is a Profiling-driven framework for enterprise-scale Text-to-gnostic analysis.<n>ProSPy structures the reasoning process into four stages.<n>It first extracts fine-grained data evidence through automatic profiling.<n>It prunes large schemas into task-relevant contexts.
  arXiv  Detail & Related papers  (2026-06-04T08:13:05Z)
• APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL [39.76924093980244]
  APEX- verbalize is a framework that shifts the paradigm from passive translation to agentic exploration.<n>Our framework employs a hypothesis-verification loop to ground model reasoning in real data.
  arXiv  Detail & Related papers  (2026-02-11T07:50:47Z)
• LLM-Based SQL Generation: Prompting, Self-Refinement, and Adaptive Weighted Majority Voting [7.590911146338215]
  We propose a Single-Agent Self-Refinement with Ensemble Voting (SSEV)<n>We build on insights from the SSEV pipeline to address the growing complexity of enterprise databases and real-world Text-to-Act tasks.<n>ReCAPAgent-5.5% integrates specialized agents for planning, external knowledge retrieval, critique, action generation, self-refinement, schema linking, and result validation.
  arXiv  Detail & Related papers  (2026-01-25T18:38:58Z)
• Boundary-Aware NL2SQL: Integrating Reliability through Hybrid Reward and Data Synthesis [23.501567675008264]
  We present BAR- Mutation (Boundary-Aware Reliable NL2), a unified training framework that embeds reliability and boundary awareness directly into the generation process.<n>We employ Knowledge-Grounded Reasoning Synthesis to ensure interpretability.
  arXiv  Detail & Related papers  (2026-01-15T11:55:01Z)
• Companion Agents: A Table-Information Mining Paradigm for Text-to-SQL [8.159121916366727]
  Large-scale Text-to-curated benchmarks such as BIRD typically assume complete and accurate database annotations as well as available external knowledge.<n>This mismatch substantially limits the real-world applicability of state-of-the-domain Text-to-art systems.<n>We propose a database-centric approach that leverages intrinsic, fine-grained information residing in relational databases to construct missing evidence.
  arXiv  Detail & Related papers  (2025-12-17T07:11:55Z)
• 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)
• RAISE: Reasoning Agent for Interactive SQL Exploration [47.77323087050061]
  We propose a novel framework that unifies schema linking, query generation, and iterative refinement within a single, end-to-end component.<n>Our method emulates how humans answer questions when working with unfamiliar databases.
  arXiv  Detail & Related papers  (2025-06-02T03:07:08Z)
• RSL-SQL: Robust Schema Linking in Text-to-SQL Generation [51.00761167842468]
  We propose a novel framework called RSL- that combines bidirectional schema linking, contextual information augmentation, binary selection strategy, and multi-turn self-correction. benchmarks demonstrate that our approach achieves SOTA execution accuracy among open-source solutions, with 67.2% on BIRD and 87.9% on GPT-4ocorrection. Our approach outperforms a series of GPT-4 based Text-to-Seek systems when adopting DeepSeek (much cheaper) with same intact prompts.
  arXiv  Detail & Related papers  (2024-10-31T16:22:26Z)
• MAG-SQL: Multi-Agent Generative Approach with Soft Schema Linking and Iterative Sub-SQL Refinement for Text-to-SQL [15.824894030016187]
  Recent In-Context Learning based methods have achieved remarkable success in Text-to-Context task. There is still a large gap between the performance of these models and human performance on datasets with complex database schema and difficult questions, such as. In our framework, an entity-based method with tables' summary is used to select the columns in database, and a novel targets-conditions decomposition method is introduced to decompose those complex questions.
  arXiv  Detail & Related papers  (2024-08-15T04:57:55Z)
• MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQL [47.120862170230566]
  Recent Text-to-yourself methods usually suffer from significant performance degradation on "huge" databases.<n>We introduce MAC, a novel Text-to-yourself LLM-based multi-agent collaborative framework.<n>In our framework, we leverage GPT-4 as the strong backbone for all agent tasks to determine the upper bound of our framework.<n>We then fine-tune an open-sourced instruction-followed model,sql-Llama, by leveraging Code 7B, to accomplish all tasks as GPT-4 does.
  arXiv  Detail & Related papers  (2023-12-18T14:40:20Z)

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.