mlsanityData to 7 Oct 2026

SIRIUS-SQL: Anchoring Multi-Candidate Text-to-SQL in Execution Feedback

arXiv 2606.01246 ↗First posted 31 May 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Text-to-SQL on complex schemas is unreliable on a single pass, so recent systems generate multiple SQL candidates and let voting filter out errors. Yet voting alone is not enough, because the multi-candidate recipe has three coupled weaknesses: 1) sampling more from a single generator produces increasingly redundant candidates, 2) existing pipelines apply one generic correction to every non-clean execution result, while runtime errors, timeouts, and empty results each indicate a different distance from correctness, and 3) existing selectors rely on a single angle such as result-majority voting or pairwise SQL comparison, missing what other angles would have caught. We present SIRIUS-SQL, which addresses all three weaknesses. A difficulty-smoothing RL recipe trains SIRIUS-32B to generate diverse executable SQL candidates, paired with a generalist LLM that fills in gaps left by the specialist. An execution-grounded lifecycle classifies each outcome and applies targeted repair before candidates re-enter the pool. A confidence-gated hybrid selector combines execution-result agreement with pairwise SQL-form judgment, escalating only near-tied cases to a deterministic structural check. SIRIUS-SQL reaches 75.88% on BIRD dev and 91.20% on SPIDER test. Two of three generalist pairings surpass Agentar-Scale-SQL, the strongest published multi-candidate system on BIRD dev.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 39 of its 44 references that are in the map. First posted on arXiv 31 May 2026.

Builds on

39 of 44 references.

References · 39

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 8,851
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  4. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scalecited by 2,678
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  6. 2023Large Language Models are not Fair Evaluatorscited by 1,050
  7. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  8. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  9. 2019RAT-SQL: Relation-Aware Schema Encoding and Linking for Text-to-SQL Parserscited by 420
  10. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  11. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  12. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
27 more
  1. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  2. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
  3. 2020Bridging Textual and Tabular Data for Cross-Domain Text-to-SQL Semantic Parsingcited by 133
  4. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  5. 2020Semantic Evaluation for Text-to-SQL with Distilled Test Suitescited by 123
  6. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 103
  7. 2025OmniSQL: Synthesizing High-quality Text-to-SQL Data at Scalecited by 90
  8. 2022RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQLcited by 85
  9. 2019Representing Schema Structure with Graph Neural Networks for Text-to-SQL Parsingcited by 74
  10. 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learningcited by 67
  11. 2021Natural SQL: Making SQL Easier to Infer from Natural Language Specificationscited by 66
  12. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  13. 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 53
  14. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 49
  15. 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
  16. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQLcited by 38
  17. 2025Alpha-SQL: Zero-Shot Text-to-SQL using Monte Carlo Tree Searchcited by 33
  18. 2024Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigmcited by 31
  19. 2024PET-SQL: A Prompt-Enhanced Two-Round Refinement of Text-to-SQL with Cross-consistencycited by 26
  20. 2025LinkAlign: Scalable Schema Linking for Real-World Large-Scale Multi-Database Text-to-SQLcited by 26
  21. 2025DeepEye-SQL: A Software-Engineering-Inspired Text-to-SQL Frameworkcited by 26
  22. 2025Agentar-Scale-SQL: Advancing Text-to-SQL through Orchestrated Test-Time Scalingcited by 20
  23. 2024Improving Retrieval-augmented Text-to-SQL with AST-based Ranking and Schema Pruningcited by 16
  24. 2025STaR-SQL: Self-Taught Reasoner for Text-to-SQLcited by 16
  25. 2025ExeSQL: Self-Taught Text-to-SQL Models with Execution-Driven Bootstrapping for SQL Dialectscited by 11
  26. 2025SPFT-SQL: Enhancing Large Language Model for Text-to-SQL Parsing by Self-Play Fine-Tuningcited by 5
  27. 2025SAFE-SQL: Self-Augmented In-Context Learning with Fine-grained Example Selection for Text-to-SQLcited by 4

Built on by

Not cited yet.