发表机构
City University of Hong Kong; Hong Kong Institute for Advanced Study, City University of Hong Kong（香港城市大学; 香港城市大学香港高等研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出面向工业过程优化的AI智能体little m，结合领域知识库与LLM交互，将现实优化问题转化为数学模型，并构建多模态基准IPC-Bench，显著优于现有大语言模型。
AI 中文摘要
制造业消耗了全球三分之一的能源，在能源效率方面仍有显著提升空间。最优过程控制对此至关重要。然而，从杂乱的真实世界工业规范中综合出数学优化模型，需要将非结构化的自然语言和空间图与严格的数学语法相衔接。这对通用大语言模型（LLMs）构成了深刻挑战，因为它们在建模连续多物理场动力学时可能会引入无效约束。为解决这一问题，我们提出了little m，一个旨在辅助工业过程控制模型构建的AI智能体。该框架将领域特定知识库与LLM驱动的交互相结合，将现实世界的优化问题表述为数学模型。为进行系统评估，我们引入了工业过程控制基准（IPC-Bench），这是一个包含50个典型场景的新型多模态数据集，需要对文本和过程图进行联合推理。通过全面的自动化结构评估和双盲人工评估，little m显著优于最先进的LLMs，能够生成语义正确的模型。这些评估关注的是建模质量，而非求解器可行性、形式物理有效性或闭环工业性能。little m的实现和IPC-Bench数据集可在以下网址获取：https URL。
英文摘要
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.
