Chatting with your ERP: A Recipe
This addresses the problem of making complex ERP systems more accessible for users in industrial settings, though it appears incremental as it builds on existing LLM and SQL generation techniques.
The paper tackled the problem of enabling natural language interaction with industrial ERP systems by developing an LLM agent that translates queries into SQL, using a novel dual-agent architecture to improve reliability.
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.