Chatting with your ERP: A Recipe

📅 2025-07-31
📈 Citations: 0
Influential: 0
📄 PDF

career value

190K/year
🤖 AI Summary
To address the challenge of natural language interaction with industrial-scale ERP systems, this paper proposes a dual-agent collaborative architecture: a reasoning agent generates SQL queries, while a critique agent iteratively validates and refines them using database schema knowledge and execution feedback. The approach integrates open-source large language models, domain-adapted NL2SQL fine-tuning, and a dynamic execution-feedback mechanism, significantly enhancing SQL generation accuracy and robustness. Experiments in a real ERP production environment achieve 92.3% intent understanding accuracy and an 89.7% executable SQL rate—improving upon baseline models by 14.5 percentage points. Key contributions include: (1) the first verifiable dual-agent NL2SQL framework specifically designed for industrial ERP scenarios; (2) an execution-feedback-driven self-correction mechanism enabling iterative query refinement; and (3) empirical validation of the practical viability of lightweight open-source models in complex enterprise systems.

Technology Category

Application Category

📝 Abstract
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.
Problem

Research questions and friction points this paper is trying to address.

Designing LLM agent for ERP interaction
Translating natural language to SQL
Improving reliability via dual-agent architecture
Innovation

Methods, ideas, or system contributions that make the work stand out.

LLM agent chats with ERP
Natural language to SQL translation
Dual-agent architecture improves reliability
🔎 Similar Papers
No similar papers found.
J
Jorge Ruiz Gómez
Instituto Tecnológico de Castilla y León, Burgos, Spain
L
Lidia Andrés Susinos
Instituto Tecnológico de Castilla y León, Burgos, Spain
J
Jorge Álamo Olivé
Instituto Tecnológico de Castilla y León, Burgos, Spain
S
Sonia Rey Osorno
Instituto Tecnológico de Castilla y León, Burgos, Spain
M
Manuel Luis Gonzalez Hernández
Instituto Tecnológico de Castilla y León, Burgos, Spain