mlsanityData to 7 Oct 2026

PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agents

arXiv 2604.17653 ↗First posted 19 Apr 2026cs.AI cs.DBcited by 5

Not on the map. Why?

Abstract (arXiv)

Text-to-SQL systems often struggle with deep contextual understanding, particularly for complex queries with subtle requirements. We present PV-SQL, an agentic framework that addresses these failures through two complementary components: Probe and Verify. The Probe component iteratively generates probing queries to retrieve concrete records from the database, resolving ambiguities in value formats, column semantics, and inter-table relationships to build richer contextual understanding. The Verify component employs a rule-based method to extract verifiable conditions and construct an executable checklist, enabling iterative SQL refinement that effectively reduces missing constraints. Experiments on the BIRD benchmarks show that PV-SQL outperforms the best text-to-SQL baseline by 5% in execution accuracy and 20.8% in valid efficiency score while consuming fewer tokens.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 32 of its 43 references that are in the map. First posted on arXiv 19 Apr 2026.

Builds on

32 of 43 references.

References · 32

  1. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  2. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,928
  3. 2018Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Taskcited by 1,120
  4. 2023Large Language Models Cannot Self-Correct Reasoning Yetcited by 965
  5. 2023Teaching Large Language Models to Self-Debugcited by 963
  6. 2023Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLscited by 667
  7. 2023DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correctioncited by 465
  8. 2022CodeT: Code Generation with Generated Testscited by 369
  9. 2023LEVER: Learning to Verify Language-to-Code Generation with Executioncited by 228
  10. 2023RESDSQL: Decoupling Schema Linking and Skeleton Parsing for Text-to-SQLcited by 191
  11. 2024CHESS: Contextual Harnessing for Efficient SQL Synthesiscited by 164
  12. 2023MAC-SQL: A Multi-Agent Collaborative Framework for Text-to-SQLcited by 158
20 more
  1. 2024CHASE-SQL: Multi-Path Reasoning and Preference Optimized Candidate Selection in Text-to-SQLcited by 132
  2. 2024Small LLMs Are Weak Tool Learners: A Multi-LLM Agentcited by 92
  3. 2024Before Generation, Align it! A Novel and Effective Strategy for Mitigating Hallucinations in Text-to-SQL Generationcited by 49
  4. 2025XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQLcited by 40
  5. 2024E-SQL: Direct Schema Linking via Question Enrichment in Text-to-SQLcited by 35
  6. 2024MAGIC: Generating Self-Correction Guideline for In-Context Text-to-SQLcited by 34
  7. 2023Interactive Text-to-SQL Generation via Editable Step-by-Step Explanationscited by 19
  8. 2024Selective Prompt Anchoring for Code Generationcited by 16
  9. 2025Understanding, Detecting, and Repairing Real-World In-Context-Learning-Based Text-to-SQL Errorscited by 14
  10. 2024Using LLM to select the right SQL Query from candidatescited by 12
  11. 2024Insights into Natural Language Database Query Errors: From Attention Misalignment to User Handling Strategiescited by 11
  12. 2024SQLucid: Grounding Natural Language Database Queries with Interactive Explanationscited by 10
  13. 2025SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQLcited by 10
  14. 2025AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQLcited by 10
  15. 2025Text-to-SQL Domain Adaptation via Human-LLM Collaborative Data Annotationcited by 6
  16. 2025SQL-of-Thought: Multi-agentic Text-to-SQL with Guided Error Correctioncited by 5
  17. 2025DCG-SQL: Enhancing In-Context Learning for Text-to-SQL with Deep Contextual Schema Link Graphcited by 4
  18. 2025RubikSQL: Lifelong Learning Agentic Knowledge Base as an Industrial NL2SQL Systemcited by 4
  19. 2025Supporting Construction Worker Well-Being with a Multi-Agent Conversational AI Systemcited by 3
  20. 2025ALLOY: Generating Reusable Agent Workflows from User Demonstrationcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 5.

5 papers.

  1. 2026Enhancing Multi-Agent Communication through Attention Steering with Context Relevancecited by 0
  2. 2026SOMA-SQL: Resolving Multi-Source Ambiguity in NL-to-SQL via Synthetic Log and Execution Probingcited by 0
  3. 2026ISEE: Interactive Semantic Enrichment for Database Fieldscited by 0
  4. 2026TraceSQL: Traceable Answerability Estimation for Reference-Free Text-to-SQL Verificationcited by 0
  5. 2026Towards Reliable AI Data Scientists: Data Agents with Workflow Harnessescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026APEX-SQL: Talking to the data via Agentic Exploration for Text-to-SQL
  2. 2026SemanticAgent: A Semantics-Aware Framework for Text-to-SQL Data Synthesis
  3. 2026FlexSQL: Flexible Exploration and Execution Make Better Text-to-SQL Agents
  4. 2025ReFoRCE: A Text-to-SQL Agent with Self-Refinement, Consensus Enforcement, and Column Exploration
  5. 2026AV-SQL: Decomposing Complex Text-to-SQL Queries with Agentic Views
  6. 2024SQLFixAgent: Towards Semantic-Accurate Text-to-SQL Parsing via Consistency-Enhanced Multi-Agent Collaboration
  7. 2025Text-to-SQL as Dual-State Reasoning: Integrating Adaptive Context and Progressive Generation
  8. 2025DB-Explore: Automated Database Exploration and Instruction Synthesis for Text-to-SQL