PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908978375557120 |
|---|---|
| author | Tian, Yuan Zhang, Tianyi |
| author_facet | Tian, Yuan Zhang, Tianyi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17653 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agents Tian, Yuan Zhang, Tianyi Artificial Intelligence Databases 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. |
| title | PV-SQL: Synergizing Database Probing and Rule-based Verification for Text-to-SQL Agents |
| topic | Artificial Intelligence Databases |
| url | https://arxiv.org/abs/2604.17653 |