AI agent improves industrial process control model building
little m: An AI Agent for Industrial Process Optimization
Artificial Intelligence
Summary
Industrial manufacturing uses a lot of energy and can get better at saving it by controlling processes in an optimal way. The authors created an AI system called little m that helps turn messy instructions and diagrams into proper math models needed for optimizing these processes. They tested little m on a new set of 50 real-world examples that mix text and diagrams and found it performed better than current language models at making correct models. This work focuses on creating good formulations rather than testing actual physical operation or solver performance.
What this means in practice
- •For industrial process engineers: Generate accurate mathematical models from complex industrial specifications to improve process optimization efforts.
- •For manufacturing software developers: Create tools that automatically convert textual and diagrammatic industrial process descriptions into formal optimization models.
Authors
Yongchao Ye, Xinyu He, Dutliff Boshoff, Way Kuo, Lishuai Li
Abstract
Manufacturing consumes one third of global energy and still has significant room for improvement in terms of energy efficiency. Optimal process control is essential for this purpose. However, synthesizing mathematical optimization models from messy, real-world industrial specifications requires bridging unstructured natural language and spatial diagrams with rigorous mathematical syntax. This poses a profound challenge for general-purpose Large Language Models (LLMs), which may introduce invalid constraints when tasked with modeling continuous multi-physics dynamics. To address this, we introduce little m, an AI agent designed to assist the formulation of industrial process control models. Combining a domain-specific knowledge repository with LLM-driven interaction, the proposed framework formulates real-world optimization problems as mathematical models. For systematic evaluation, we introduce the Industrial Process Control Benchmark (IPC-Bench), a novel multimodal dataset of 50 canonical scenarios requiring joint reasoning over text and process diagrams. Through comprehensive automated structural assessments and double-blind human evaluation, little m substantially outperforms state-of-the-art LLMs, generating semantically correct models. These evaluations assess formulation quality rather than solver feasibility, formal physical validity, or closed-loop industrial performance. The implementation of little m and the IPC-Bench dataset are available at https://github.com/yeyongchao/process-modeling-benchmark.