Chatting with your ERP: A Recipe
Jorge Ruiz G\'omez, Lidia Andr\'es Susinos, Jorge Alamo Oliv\'e, Sonia Rey Osorno, Manuel Luis Gonzalez Hern\'andez
TL;DR
This paper introduces an LLM-based agent that interacts with an ERP system through natural language, translating queries into SQL with a novel architecture to enhance reliability.
Contribution
It presents a new dual-agent architecture for reliable natural language to SQL translation in industrial ERP systems.
Findings
Effective natural language querying of ERP systems demonstrated.
Improved query accuracy with the dual-agent architecture.
Potential for broader adoption in industrial settings.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsERP Systems Implementation and Impact