From Questions to Queries: An AI-powered Multi-Agent Framework for Spatial Text-to-SQL

2025-10-23

AI Summary

Non-experts face significant barriers in effectively analyzing geospatial data due to the steep learning curve of SQL and spatial tools like PostGIS. To address this, we propose a collaborative multi-agent framework that overcomes key limitations of single-agent approaches in spatial Text-to-SQL tasks—particularly in semantic understanding and modeling of complex spatial predicates. Our method innovatively integrates procedural pattern analysis, a semantics-enhanced knowledge base, and a self-verification mechanism, unifying embedding-based retrieval, entity/metadata extraction, logical modeling, and SQL generation. A novel syntax–semantics dual verification module further ensures correctness and intent alignment. Evaluated on KaggleDBQA and our newly constructed SpatialQueryQA benchmark, our framework achieves 81.2% and 87.7% exact-match accuracy, respectively—substantially outperforming unverified baselines and yielding queries with markedly improved fidelity to user intent.

Technology Category

• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning
• Data Mining & Knowledge Management: Mining of Spatial, Temporal or Spatio-Temporal Data
• Natural Language Processing: Question Answering

Application Category

• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Querying, indexing, and retrieval in Web-related graphs

Abstract

The complexity of Structured Query Language (SQL) and the specialized nature of geospatial functions in tools like PostGIS present significant barriers to non-experts seeking to analyze spatial data. While Large Language Models (LLMs) offer promise for translating natural language into SQL (Text-to-SQL), single-agent approaches often struggle with the semantic and syntactic complexities of spatial queries. To address this, we propose a multi-agent framework designed to accurately translate natural language questions into spatial SQL queries. The framework integrates several innovative components, including a knowledge base with programmatic schema profiling and semantic enrichment, embeddings for context retrieval, and a collaborative multi-agent pipeline as its core. This pipeline comprises specialized agents for entity extraction, metadata retrieval, query logic formulation, SQL generation, and a review agent that performs programmatic and semantic validation of the generated SQL to ensure correctness (self-verification). We evaluate our system using both the non-spatial KaggleDBQA benchmark and a new, comprehensive SpatialQueryQA benchmark that includes diverse geometry types, predicates, and three levels of query complexity. On KaggleDBQA, the system achieved an overall accuracy of 81.2% (221 out of 272 questions) after the review agent's review and corrections. For spatial queries, the system achieved an overall accuracy of 87.7% (79 out of 90 questions), compared with 76.7% without the review agent. Beyond accuracy, results also show that in some instances the system generates queries that are more semantically aligned with user intent than those in the benchmarks. This work makes spatial analysis more accessible, and provides a robust, generalizable foundation for spatial Text-to-SQL systems, advancing the development of autonomous GIS.

Problem

• Translating natural language questions into spatial SQL queries for non-experts
• Overcoming semantic and syntactic complexities in spatial query generation
• Improving accuracy of spatial Text-to-SQL systems through multi-agent collaboration

Innovation

• Multi-agent framework for spatial text-to-SQL translation
• Knowledge base with schema profiling and semantic enrichment
• Review agent performs programmatic and semantic SQL validation