EvoAgent-SQL: An Evolutionary Multi-Agent Text2SQL Framework Integrating User Feedback and Reflective Adaptation

doi:10.3390/sym18050792

Return

EvoAgent-SQL: An Evolutionary Multi-Agent Text2SQL Framework Integrating User Feedback and Reflective Adaptation

2026-05-06

DOI：10.3390/sym18050792

Original

Original request for help

Save

Abstract

En 中文

Natural language to structured query language (Text2SQL) is a critical task in intelligent question answering and database interaction. A fundamental challenge lies in achieving semantic symmetry between natural language expressions and database schemas, as well as behavioral symmetry between query generation and error correction. Traditional approaches often struggle with comprehending domain-specific concepts and dynamically adapting to user's feedback, breaking the desired symmetry between system output and user intent. Thispaper presents EvoAgent-SQL as a lightweight engineering framework for private domain data querying based on low-cost lightweight models. The framework comprises three core agents: (1) the Schema Grounding Agent (SGA) establishes a symmetric mapping from natural language concepts to database fields; (2) the Execution Agent (EA) generates SQL queries; and (3) the Reflection Agent (RA) mirrors the EA's outputs by analyzing errors and proposing corrections, forming a reflective symmetry loop. When ambiguity arises, user feedback is incorporated as a symmetry-breaking signal, which the RA uses to restore alignment through iterative evolution with a memory mechanism. We evaluate the framework on an education-domain dataset and provide a reproducibility plan for releasing sanitized schemas, natural language questions, and reference SQL while withholding confidential institutional records. Experimental results demonstrate that EvoAgent-SQL enhances query execution accuracy, achieving a 13.7% reduction in the relative error residual after one evolution cycle and a 17.6% cumulative reduction after two cycles, suggesting practical adaptability in domain-specific Text2SQL tasks.

Keywords:

human-computer interaction

Text2SQL

multi-agent system

symmetry and evolutionary mechanism

user feedback

reflective learning