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

2026-03-03

AI Summary

This work addresses the challenge that large language models often generate uncompilable optimization code when automatically translating natural language requirements due to type mismatches, missing declarations, and incomplete context. To overcome this, the authors propose a type-aware retrieval-augmented generation (RAG) approach that integrates a type system and dependency closure mechanism into the RAG framework for the first time. By constructing a domain-specific, typed knowledge graph and combining hybrid retrieval with a dependency propagation algorithm, the method produces structurally correct models satisfying minimal dependency closure. Evaluated on two industrial use cases—battery production demand response and flexible job shop scheduling—the approach successfully generates compilable models that achieve known optimal solutions, significantly outperforming conventional RAG baselines.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Planning, Routing, and Scheduling: Planning with Language Models
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Automated industrial optimization modeling requires reliable translation of natural-language requirements into solver-executable code. However, large language models often generate non-compilable models due to missing declarations, type inconsistencies, and incomplete dependency contexts. We propose a type-aware retrieval-augmented generation (RAG) method that enforces modeling entity types and minimal dependency closure to ensure executability. Unlike existing RAG approaches that index unstructured text, our method constructs a domain-specific typed knowledge base by parsing heterogeneous sources, such as academic papers and solver code, into typed units and encoding their mathematical dependencies in a knowledge graph. Given a natural-language instruction, it performs hybrid retrieval and computes a minimal dependency-closed context, the smallest set of typed symbols required for solver-executable code, via dependency propagation over the graph. We validate the method on two constraint-intensive industrial cases: demand response optimization in battery production and flexible job shop scheduling. In the first case, our method generates an executable model incorporating demand-response incentives and load-reduction constraints, achieving peak shaving while preserving profitability; conventional RAG baselines fail. In the second case, it consistently produces compilable models that reach known optimal solutions, demonstrating robust cross-domain generalization; baselines fail entirely. Ablation studies confirm that enforcing type-aware dependency closure is essential for avoiding structural hallucinations and ensuring executability, addressing a critical barrier to deploying large language models in complex engineering optimization tasks.

Problem

• industrial optimization modeling
• solver-executable code
• type inconsistency
• dependency closure
• natural-language requirements

Innovation

• type-aware retrieval-augmented generation
• dependency closure
• solver-executable modeling
• typed knowledge graph
• industrial optimization