Beyond Text-to-SQL: Autonomous Research-Driven Database Exploration with DAR
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915787865849856 |
|---|---|
| author | Vykhopen, Ostap Skorik, Viktoria Tereshchenko, Maksym Solopova, Veronika |
| author_facet | Vykhopen, Ostap Skorik, Viktoria Tereshchenko, Maksym Solopova, Veronika |
| contents | Large language models can already query databases, yet most existing systems remain reactive: they rely on explicit user prompts and do not actively explore data. We introduce DAR (Data Agnostic Researcher), a multi-agent system that performs end-to-end database research without human-initiated queries. DAR orchestrates specialized AI agents across three layers: initialization (intent inference and metadata extraction), execution (SQL and AI-based query synthesis with iterative validation), and synthesis (report generation with built-in quality control). All reasoning is executed directly inside BigQuery using native generative AI functions, eliminating data movement and preserving data governance. On a realistic asset-incident dataset, DAR completes the full analytical task in 16 minutes, compared to 8.5 hours for a professional analyst (approximately 32x times faster), while producing useful pattern-based insights and evidence-grounded recommendations. Although human experts continue to offer deeper contextual interpretation, DAR excels at rapid exploratory analysis. Overall, this work shifts database interaction from query-driven assistance toward autonomous, research-driven exploration within cloud data warehouses. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_14622 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Text-to-SQL: Autonomous Research-Driven Database Exploration with DAR Vykhopen, Ostap Skorik, Viktoria Tereshchenko, Maksym Solopova, Veronika Databases Large language models can already query databases, yet most existing systems remain reactive: they rely on explicit user prompts and do not actively explore data. We introduce DAR (Data Agnostic Researcher), a multi-agent system that performs end-to-end database research without human-initiated queries. DAR orchestrates specialized AI agents across three layers: initialization (intent inference and metadata extraction), execution (SQL and AI-based query synthesis with iterative validation), and synthesis (report generation with built-in quality control). All reasoning is executed directly inside BigQuery using native generative AI functions, eliminating data movement and preserving data governance. On a realistic asset-incident dataset, DAR completes the full analytical task in 16 minutes, compared to 8.5 hours for a professional analyst (approximately 32x times faster), while producing useful pattern-based insights and evidence-grounded recommendations. Although human experts continue to offer deeper contextual interpretation, DAR excels at rapid exploratory analysis. Overall, this work shifts database interaction from query-driven assistance toward autonomous, research-driven exploration within cloud data warehouses. |
| title | Beyond Text-to-SQL: Autonomous Research-Driven Database Exploration with DAR |
| topic | Databases |
| url | https://arxiv.org/abs/2512.14622 |