From Queries to Insights: Agentic LLM Pipelines for Spatio-Temporal Text-to-SQL
This work addresses the challenge of enabling users without SQL expertise to query databases more effectively, particularly for spatio-temporal data, though it appears incremental as it builds on existing models and tools.
The paper tackled the problem of natural-language-to-SQL systems struggling with realistic spatio-temporal queries by introducing an agentic pipeline that extends a baseline model with orchestration, achieving 91.4% accuracy compared to 28.6% for the baseline on a dataset of 35 queries.
Natural-language-to-SQL (NL-to-SQL) systems hold promise for democratizing access to structured data, allowing users to query databases without learning SQL. Yet existing systems struggle with realistic spatio-temporal queries, where success requires aligning vague user phrasing with schema-specific categories, handling temporal reasoning, and choosing appropriate outputs. We present an agentic pipeline that extends a naive text-to-SQL baseline (llama-3-sqlcoder-8b) with orchestration by a Mistral-based ReAct agent. The agent can plan, decompose, and adapt queries through schema inspection, SQL generation, execution, and visualization tools. We evaluate on 35 natural-language queries over the NYC and Tokyo check-in dataset, covering spatial, temporal, and multi-dataset reasoning. The agent achieves substantially higher accuracy than the naive baseline 91.4% vs. 28.6% and enhances usability through maps, plots, and structured natural-language summaries. Crucially, our design enables more natural human-database interaction, supporting users who lack SQL expertise, detailed schema knowledge, or prompting skill. We conclude that agentic orchestration, rather than stronger SQL generators alone, is a promising foundation for interactive geospatial assistants.