arXiv:2507.23429cs.AIcs.DB2025-07被引 1

让大模型直接对话企业核心系统,自然语言变查询语句

Chatting with your ERP: A Recipe

  • 用双阶段代理架构,先推理后自检提升生成可靠性
  • 基于开源大模型实现自然语言转可执行SQL
  • 适合想对接企业ERP的开发者与产品经理

本文介绍了一个大型语言模型(LLM)代理的设计、实现与评估,该代理可与工业级生产型企业资源计划(ERP)系统进行对话。代理能够理解自然语言查询,并将其转化为可执行的SQL语句,利用开源权重的LLM实现。提出一种新颖的双代理架构,包含推理与批判两个阶段,以提高查询生成的可靠性。

原文摘要 · Abstract (English)

This paper presents the design, implementation, and evaluation behind a Large Language Model (LLM) agent that chats with an industrial production-grade ERP system. The agent is capable of interpreting natural language queries and translating them into executable SQL statements, leveraging open-weight LLMs. A novel dual-agent architecture combining reasoning and critique stages was proposed to improve query generation reliability.

大模型ERP自然语言转SQL

Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品;中文卡片由大模型生成,请以原文为准。