{"ID":2828618,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.14622","arxiv_id":"2512.14622","title":"Beyond Text-to-SQL: Autonomous Research-Driven Database Exploration with DAR","abstract":"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.","short_abstract":"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 orchestrate...","url_abs":"https://arxiv.org/abs/2512.14622","url_pdf":"https://arxiv.org/pdf/2512.14622v2","authors":"[\"Ostap Vykhopen\",\"Viktoria Skorik\",\"Maksym Tereshchenko\",\"Veronika Solopova\"]","published":"2025-12-16T17:36:09Z","proceeding":"cs.DB","tasks":"[\"cs.DB\"]","methods":"[\"Language Model\",\"LoRA\"]","has_code":false}