Type-Aware Retrieval-Augmented Generation with Dependency Closure for Solver-Executable Industrial Optimization Modeling

Researchers developed a type-aware retrieval-augmented generation (RAG) method that translates natural language requirements into solver-executable optimization code for industrial applications. The method uses a typed knowledge base and dependency closure to ensure code executability, successfully validated on battery production optimization and job scheduling tasks where conventional RAG approaches failed.

• →New RAG method solves critical issue of large language models generating non-compilable optimization code due to missing declarations and type inconsistencies.
• →The approach constructs domain-specific typed knowledge bases by parsing academic papers and solver code into mathematical dependency graphs.
• →Method successfully generated executable models for demand response optimization in battery production and flexible job shop scheduling.
• →Conventional RAG baselines failed completely on both industrial test cases, demonstrating significant improvement in reliability.
• →Research addresses a major barrier to deploying LLMs in complex engineering optimization tasks across industries.