SchemaAgent: A Multi-Agents Framework for Generating Relational Database Schema

2025-03-31

AI Summary

Automatically translating natural language requirements into relational database schemas remains challenging due to reliance on domain expertise, low accuracy, and poor generalization in existing approaches. Method: This paper introduces RSchema—the first large language model (LLM)-based multi-agent framework for schema generation—featuring a novel “reflection–quality assurance” dual-role collaboration mechanism. It integrates specialized role division, cross-stage error detection, and structured correction techniques. Contribution/Results: Evaluated on the newly constructed RSchema benchmark (500+ high-quality requirement-schema pairs), our method significantly outperforms state-of-the-art LLMs and conventional methods: schema accuracy and completeness improve by 28.6% and 34.1%, respectively. RSchema achieves, for the first time, end-to-end, high-fidelity, and interpretable relational schema generation without manual intervention.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

The relational database design would output a schema based on user's requirements, which defines table structures and their interrelated relations. Translating requirements into accurate schema involves several non-trivial subtasks demanding both database expertise and domain-specific knowledge. This poses unique challenges for automated design of relational databases. Existing efforts are mostly based on customized rules or conventional deep learning models, often producing suboptimal schema. Recently, large language models (LLMs) have significantly advanced intelligent application development across various domains. In this paper, we propose SchemaAgent, a unified LLM-based multi-agent framework for the automated generation of high-quality database schema. SchemaAgent is the first to apply LLMs for schema generation, which emulates the workflow of manual schema design by assigning specialized roles to agents and enabling effective collaboration to refine their respective subtasks. Schema generation is a streamlined workflow, where directly applying the multi-agent framework may cause compounding impact of errors. To address this, we incorporate dedicated roles for reflection and inspection, alongside an innovative error detection and correction mechanism to identify and rectify issues across various phases. For evaluation, we present a benchmark named extit{RSchema}, which contains more than 500 pairs of requirement description and schema. Experimental results on this benchmark demonstrate the superiority of our approach over mainstream LLMs for relational database schema generation.

Problem

• Automating relational database schema design from user requirements
• Overcoming limitations of rule-based and conventional deep learning methods
• Ensuring accuracy in multi-agent collaboration for schema generation

Innovation

• LLM-based multi-agent framework for schema generation
• Specialized roles and collaboration for subtasks refinement
• Error detection and correction mechanism across phases