Cooperative SQL Generation for Segmented Databases By Using Multi-functional LLM Agents

TL;DR

This paper introduces a cooperative framework using multi-functional LLM agents for text-to-SQL tasks in segmented databases, enhancing privacy and achieving competitive performance.

Contribution

It presents a novel multi-agent collaboration approach for SQL generation that maintains data privacy and improves accuracy in segmented database environments.

Findings

Achieves performance comparable to state-of-the-art methods.

Maintains data privacy by keeping schemas within individual agents.

Effective collaboration among agents improves SQL query accuracy.

Abstract

Text-to-SQL task aims to automatically yield SQL queries according to user text questions. To address this problem, we propose a Cooperative SQL Generation framework based on Multi-functional Agents (CSMA) through information interaction among large language model (LLM) based agents who own part of the database schema seperately. Inspired by the collaboration in human teamwork, CSMA consists of three stages: 1) Question-related schema collection, 2) Question-corresponding SQL query generation, and 3) SQL query correctness check. In the first stage, agents analyze their respective schema and communicate with each other to collect the schema information relevant to the question. In the second stage, agents try to generate the corresponding SQL query for the question using the collected information. In the third stage, agents check if the SQL query is created correctly according to their known information. This interaction-based method makes the question-relevant part of database schema from each agent to be used for SQL generation and check. Experiments on the Spider and Bird benckmark demonstrate that CSMA achieves a high performance level comparable to the state-of-the-arts, meanwhile holding the private data in these individual agents.