mlsanityData to 7 Oct 2026

Residual Skill Optimization for Text-to-SQL Ensembles

arXiv 2605.21792 ↗First posted 20 May 2026cs.CL cs.AI cs.DBcited by 0

Not on the map. Why?

Abstract (arXiv)

Text-to-SQL ensembles improve over single-candidate generation by drawing multiple SQL candidates and selecting one, but their effectiveness is bounded by Pass@K, the probability that at least one of K candidates is correct. Existing methods source diversity heuristically through stochastic decoding or prompt variants, leaving candidate sets dominated by correlated failures. We present DivSkill-SQL, a residual skill optimization framework that builds complementary agentic Text-to-SQL ensembles without model fine-tuning: each new skill is optimized on examples the current skill ensemble fails on, provably targeting its marginal contribution to Pass@K. On Spider2-Lite, DivSkill-SQL improves selected accuracy by up to +11.1 points on Snowflake and +8.3 on BigQuery over the strongest ensemble baseline, with consistent gains across two base models (Opus-4.6 and GPT-5.4). Skills optimized on a single dialect transfer without retraining across dialects (Snowflake, BigQuery, SQLite) and to a different task formulation, such as BIRD-Critic (+2.6 pts). Error diagnostics show up to 3x fewer hallucinated schema references and function calls, indicating that gains come from genuinely reliable complementary skills rather than surface-form variation.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 45 of its 53 references that are in the map. First posted on arXiv 20 May 2026.

Builds on

45 of 53 references.

References · 45

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2023Let's Verify Step by Stepcited by 3,598
  5. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  6. 2022Large Language Models Are Human-Level Prompt Engineerscited by 1,020
  7. 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?cited by 948
  8. 2023Large Language Models as Optimizerscited by 830
  9. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  10. 2023Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolutioncited by 521
  11. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  12. 2025GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningcited by 449
33 more
  1. 2023Text-to-SQL Empowered by Large Language Models: A Benchmark Evaluationcited by 378
  2. 2026SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learningcited by 252
  3. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  4. 2024Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflowscited by 223
  5. 2024V-STaR: Training Verifiers for Self-Taught Reasonerscited by 214
  6. 2024CodeS: Towards Building Open-source Language Models for Text-to-SQLcited by 183
  7. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  8. 2023C3: Zero-shot Text-to-SQL with ChatGPTcited by 159
  9. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
  10. 2025Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Modelscited by 134
  11. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  12. 2026MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agentscited by 129
  13. 2026CoEvoSkills: Self-Evolving Agent Skills via Co-Evolutionary Verificationcited by 117
  14. 2024MCS-SQL: Leveraging Multiple Prompts and Multiple-Choice Selection For Text-to-SQL Generationcited by 103
  15. 2025Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problemscited by 83
  16. 2024The Dawn of Natural Language to SQL: Are We Fully Ready?cited by 78
  17. 2026SkillClaw: Let Skills Evolve Collectively with Agentic Evolvercited by 76
  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 67
  20. 2025Reasoning-SQL: Reinforcement Learning with SQL Tailored Partial Rewards for Reasoning-Enhanced Text-to-SQLcited by 59
  21. 2026Memento-Skills: Let Agents Design Agentscited by 56
  22. 2024Synthesizing Text-to-SQL Data from Weak and Strong LLMscited by 53
  23. 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
  24. 2025Diversity-Aware Policy Optimization for Large Language Model Reasoningcited by 39
  25. 2023Boosted Prompt Ensembles for Large Language Modelscited by 36
  26. 2023Evaluating Cross-Domain Text-to-SQL Models and Benchmarkscited by 32
  27. 2024Decomposition for Enhancing Attention: Improving LLM-based Text-to-SQL through Workflow Paradigmcited by 31
  28. 2025ExCoT: Optimizing Reasoning for Text-to-SQL with Execution Feedbackcited by 23
  29. 2025Reliable Text-to-SQL with Adaptive Abstentioncited by 19
  30. 2025SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applicationscited by 15
  31. 2025MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQLcited by 14
  32. 2025SQLForge: Synthesizing Reliable and Diverse Data to Enhance Text-to-SQL Reasoning in LLMscited by 10
  33. 2024Structure Guided Large Language Model for SQL Generationcited by 9

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024SQL-GEN: Bridging the Dialect Gap for Text-to-SQL Via Synthetic Data And Model Merging
  2. 2026R3-SQL: Ranking Reward and Resampling for Text-to-SQL
  3. 2026LIMIT: Less Is More for Instruction Tuning in Text-to-SQL
  4. 2024SelECT-SQL: Self-correcting ensemble Chain-of-Thought for Text-to-SQL
  5. 2026SQL-Zero: Self-Evolving Text-to-SQL
  6. 2024ROUTE: Robust Multitask Tuning and Collaboration for Text-to-SQL
  7. 2025Arctic-Text2SQL-R1: Simple Rewards, Strong Reasoning in Text-to-SQL
  8. 2025JudgeSQL: Reasoning over SQL Candidates with Weighted Consensus Tournament