mlsanityData to 14 Oct 2026

Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL

arXiv 2505.20315 ↗First posted 22 May 2025cs.CL cs.AIcited by 38

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

Translating natural language into SQL (Test2SQL) is a longstanding challenge at the intersection of natural language understanding and structured data access. While large language models (LLMs) have significantly improved fluency in SQL generation, producing correct and executable SQL--particularly for complex queries--remains a bottleneck. We present Arctic-Text2SQL-R1, a reinforcement learning (RL) framework and model family designed to generate accurate, executable SQL using a lightweight reward signal based solely on execution correctness. Our approach avoids brittle intermediate supervision and complex reward shaping, promoting stable training and alignment with the end task. Combined with carefully curated data, strong supervised initialization, and effective training practices, Arctic-Text2SQL-R1 achieves state-of-the-art execution accuracy across six diverse Test2SQL benchmarks, including the top position on the BIRD leaderboard. Notably, our 7B model outperforms prior 70B-class systems, highlighting the framework's scalability and efficiency. We further demonstrate inference-time robustness through simple extensions like value retrieval and majority voting. Extensive experiments and ablation studies offer both positive and negative insights, providing practical guidance for future Test2SQL research.

Key facts. Cited by 38 papers in the map (data through 14 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 44 of its 57 references that are in the map. First posted on arXiv 22 May 2025.

Builds on

44 of 57 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Think2SQL: Reinforce LLM Reasoning Capabilities for Text2SQL21 Apr
  2. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQL29 Mar
  3. 2025ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedback25 Mar
  4. 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQL19 Feb

Other references · 40

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2024The Llama 3 Herd of Modelscited by 14,715
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  4. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  5. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  6. 2024Qwen2.5 Technical Reportcited by 4,942
  7. 2024Mixtral of Expertscited by 1,823
  8. 2024OpenAI o1 System Cardcited by 1,244
  9. 2024Qwen2.5-Coder Technical Reportcited by 1,203
  10. 2024DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligencecited by 1,181
  11. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,139
  12. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
28 more
  1. 2024Tulu 3: Pushing Frontiers in Open Language Model Post-Trainingcited by 1,053
  2. 2024DeepSeek-V3 Technical Reportcited by 811
  3. 2017Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learningcited by 687
  4. 2024StarCoder 2 and The Stack v2: The Next Generationcited by 502
  5. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 424
  6. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 385
  7. 2024DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligencecited by 331
  8. 2025Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Modelscited by 293
  9. 2025Logic-RL: Unleashing LLM Reasoning with Rule-Based Reinforcement Learningcited by 262
  10. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 169
  11. 2025LLM Post-Training: A Deep Dive into Reasoning Large Language Modelscited by 135
  12. 2024OpenCoder: The Open Cookbook for Top-Tier Code Large Language Modelscited by 130
  13. 2025Competitive Programming with Large Reasoning Modelscited by 119
  14. 2024Granite Code Models: A Family of Open Foundation Models for Code Intelligencecited by 117
  15. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 91
  16. 2024Enhancing Code LLMs with Reinforcement Learning in Code Generation: A Surveycited by 83
  17. 2025Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn'tcited by 74
  18. 2023Exploring Chain-of-Thought Style Prompting for Text-to-SQLcited by 69
  19. 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learningcited by 68
  20. 2025Command A: An Enterprise-Ready Large Language Modelcited by 59
  21. 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 54
  22. 2025Code to Think, Think to Code: A Survey on Code-Enhanced Reasoning and Reasoning-Driven Code Intelligence in LLMscited by 47
  23. 2024A Preview of XiYan-SQL: A Multi-Generator Ensemble Framework for Text-to-SQLcited by 46
  24. 2023ScienceBenchmark: A Complex Real-World Benchmark for Evaluating Natural Language to SQL Systemscited by 45
  25. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Explorationcited by 37
  26. 2024Knowledge-to-SQL: Enhancing SQL Generation with Data Expert LLMcited by 35
  27. 2024Large Language Model Enhanced Text-to-SQL Generation: A Surveycited by 24
  28. 2024A Survey of Large Language Model-Based Generative AI for Text-to-SQL: Benchmarks, Applications, Use Cases, and Challengescited by 10

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 27.

38 papers.

Sort:

By area:

  1. 2025Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scalingcited by 24
  2. 2025MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQLcited by 15
  3. 2026AgentSM: Semantic Memory for Agentic Text-to-SQLcited by 14
  4. 2026Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RLcited by 14
  5. 2025SLM-SQL: An Exploration of Small Language Models for Text-to-SQLcited by 10
  6. 2025MTIR-SQL: Multi-turn Tool-Integrated Reasoning Reinforcement Learning for Text-to-SQLcited by 10
  7. 2025Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generationcited by 10
  8. 2025SING-SQL: A Synthetic Data Generation Framework for In-Domain Text-to-SQL Translationcited by 5
  9. 2025RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL Systemcited by 4
  10. 2025Agent Bain vs. Agent McKinsey: A New Text-to-SQL Benchmark for the Business Domaincited by 4
  11. 2026Learning to Self-Evolvecited by 4
  12. 2026SQL-ASTRA: Alleviating Sparse Feedback in Agentic SQL via Column-Set Matching and Trajectory Aggregationcited by 3
26 more
  1. 2026TRUST-SQL: Tool-Integrated Multi-Turn Reinforcement Learning for Text-to-SQL over Unknown Schemascited by 3
  2. 2025PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learningcited by 2
  3. 2025AGRO-SQL: Agentic Group-Relative Optimization with High-Fidelity Data Synthesiscited by 2
  4. 2025Knowledge Distillation with Structured Chain-of-Thought for Text-to-SQLcited by 1
  5. 2026EvolSQL: Structure-Aware Evolution for Scalable Text-to-SQL Data Synthesiscited by 1
  6. 2026Beyond Static Pipelines: Learning Dynamic Workflows for Text-to-SQLcited by 1
  7. 2026Human-Level Text-to-SQL via Reinforcement Learning on Verified Data, Without Pipeline Engineeringcited by 1
  8. 2026PExA: Parallel Exploration Agent for Complex Text-to-SQLcited by 1
  9. 2026R3-SQL: Ranking Reward and Resampling for Text-to-SQLcited by 1
  10. 2026Every Step Counts: Step-Level Credit Assignment for Tool-Integrated Text-to-SQLcited by 1
  11. 2026SQLConductor: Search-to-Policy Learning for Step-wise Text-to-SQL Orchestrationcited by 1
  12. 2026EXPO-SQL: Execution-based Clause-level Policy Optimization for Text-to-SQLcited by 1
  13. 2026SQLMorph: Query Mutation and Fine-Grained Metrics for Text-to-SQL Evaluationcited by 1
  14. 2026RingSQL: Schema-Independent Synthetic Data Generation for Text-to-SQL Reinforcement Learningcited by 0
  15. 2026IESR:Efficient MCTS-Based Modular Reasoning for Text-to-SQL with Large Language Modelscited by 0
  16. 2026Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decodingcited by 0
  17. 2026FINER-SQL: Boosting Small Language Models for Text-to-SQLcited by 0
  18. 2026SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedbackcited by 0
  19. 2026ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQLcited by 0
  20. 2026Benchmarking Text-to-SQL under Role-Based Access Controlcited by 0
  21. 2026Learning When to Reason for Text-to-SQL via SFT and DPOcited by 0
  22. 2026SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learningcited by 0
  23. 2026From Test-Time Scaling to Reusable Memory: Measuring Crystallization in Text-to-SQLcited by 0
  24. 2026Replacing Training with Memory: Listwise Selection for Text-to-SQLcited by 0
  25. 2026DualSQL: Text-to-SQL with Multi-Agent Reinforcement Learningcited by 0
  26. 2026COAL-SQL: Coverage-Guided Augmentation and Failure-Driven Learning for Text-to-SQL Post-Trainingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025CogniSQL-R1-Zero: Lightweight Reinforced Reasoning for Efficient SQL Generation
  2. 2026Progress-SQL: Improving Reinforcement Learning for Text-to-SQL via Progressive Rewards
  3. 2025JudgeSQL: Reasoning over SQL Candidates with Weighted Consensus Tournament
  4. 2025GradeSQL: Test-Time Inference with Outcome Reward Models for Text-to-SQL Generation from Large Language Models
  5. 2025SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL
  6. 2025Beyond Query-Level Comparison: Fine-Grained Reinforcement Learning for Text-to-SQL with Automated Interpretable Critiques
  7. 2025Reward-SQL: Boosting Text-to-SQL via Stepwise Execution-Aware Reasoning and Process-Supervised Rewards
  8. 2025Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning