little m: An AI Agent for Industrial Process Optimization

• URL: http://arxiv.org/abs/2609.16680v1
• Date: Tue, 15 Sep 2026 06:01:18 GMT
• Title: little m: An AI Agent for Industrial Process Optimization
• Abstract summary: We introduce little m, an AI agent designed to assist the formulation of industrial process control models.<n>For systematic evaluation, we introduce the Industrial Process Control Benchmark (IPC-Bench), a novel dataset of 50 canonical scenarios.<n>Little m substantially outperforms state-of-the-art LLMs, generating semantically correct models.
• Score: 6.819597984555337
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Opti-Agent-Bench: Benchmarking End-to-End Optimization R&D Agents on Real-World Business Problems [1.7689718394104148]
  LLM-based agents are increasingly deployed to solve optimization problems, yet existing benchmarks evaluate them on pre-structured benchmarks.<n>We introduce an end-to-end benchmark that evaluates Large Models (LLMs) from implementation through integer code, descriptions and report generation.
  arXiv  Detail & Related papers  (2026-07-12T13:47:57Z)
• Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification [53.763212981479455]
  We propose a novel framework with Dual-side Verification (Opt-Verifier) from both structure and solution perspectives.<n> Experiments on popular benchmarks demonstrate that our approach achieves over 20% improvement in accuracy.
  arXiv  Detail & Related papers  (2026-05-28T08:09:52Z)
• Automating modeling in mechanics: LLMs as designers of physics-constrained neural networks for constitutive modeling of materials [0.0]
  Large language model (LLM)-based agentic frameworks increasingly adopt the paradigm of dynamically generating task-specific agents.<n>We suggest that not only agents but also specialized software modules for scientific and engineering tasks can be generated on demand.
  arXiv  Detail & Related papers  (2025-12-01T14:42:22Z)
• Automated Optimization Modeling through Expert-Guided Large Language Model Reasoning [43.63419208391747]
  We present a novel framework that leverages expert-level optimization modeling principles through chain-of-thought reasoning to automate the optimization process.<n>We also introduce LogiOR, a new optimization modeling benchmark from the logistics domain, containing more complex problems with standardized annotations.
  arXiv  Detail & Related papers  (2025-08-20T04:14:54Z)
• Data-Driven Differential Evolution in Tire Industry Extrusion: Leveraging Surrogate Models [0.0]
  This study proposes a surrogate-based, data-driven methodology for optimizing complex real-world manufacturing systems.<n>Machine learning models are employed to approximate system behavior and construct surrogate models, which are integrated into a tailored metaheuristic approach.<n>Results show that the surrogate-based optimization approach outperforms historical best configurations.
  arXiv  Detail & Related papers  (2025-07-15T10:52:45Z)
• ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges [72.19809898215857]
  We introduce ModelingBench, a novel benchmark featuring real-world-inspired, open-ended problems from math modeling competitions across diverse domains.<n>These tasks require translating natural language into formal mathematical formulations, applying appropriate tools, and producing structured, defensible reports.<n>We also present ModelingAgent, a multi-agent framework that coordinates tool use, supports structured, creative solutions, and generates well-grounded, creative solutions.
  arXiv  Detail & Related papers  (2025-05-21T03:33:23Z)
• MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering [57.156093929365255]
  Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents.<n>MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios.<n>Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning.
  arXiv  Detail & Related papers  (2025-05-12T17:35:43Z)
• Automatic Evaluation for Text-to-image Generation: Task-decomposed Framework, Distilled Training, and Meta-evaluation Benchmark [62.58869921806019]
  We propose a task decomposition evaluation framework based on GPT-4o to automatically construct a new training dataset. We design innovative training strategies to effectively distill GPT-4o's evaluation capabilities into a 7B open-source MLLM, MiniCPM-V-2.6. Experimental results demonstrate that our distilled open-source MLLM significantly outperforms the current state-of-the-art GPT-4o-base baseline.
  arXiv  Detail & Related papers  (2024-11-23T08:06:06Z)
• ORLM: A Customizable Framework in Training Large Models for Automated Optimization Modeling [15.67321902882617]
  We propose a viable path for training open-source LLMs capable of optimization modeling and developing solver codes.<n>This work also introduces IndustryOR, the first industrial benchmark for evaluating LLMs in solving practical OR problems.
  arXiv  Detail & Related papers  (2024-05-28T01:55:35Z)
• Machine Learning Insides OptVerse AI Solver: Design Principles and Applications [74.67495900436728]
  We present a comprehensive study on the integration of machine learning (ML) techniques into Huawei Cloud's OptVerse AI solver. We showcase our methods for generating complex SAT and MILP instances utilizing generative models that mirror multifaceted structures of real-world problem. We detail the incorporation of state-of-the-art parameter tuning algorithms which markedly elevate solver performance.
  arXiv  Detail & Related papers  (2024-01-11T15:02:15Z)
• QualEval: Qualitative Evaluation for Model Improvement [82.73561470966658]
  We propose QualEval, which augments quantitative scalar metrics with automated qualitative evaluation as a vehicle for model improvement. QualEval uses a powerful LLM reasoner and our novel flexible linear programming solver to generate human-readable insights. We demonstrate that leveraging its insights, for example, improves the absolute performance of the Llama 2 model by up to 15% points relative.
  arXiv  Detail & Related papers  (2023-11-06T00:21:44Z)
• Generating Hidden Markov Models from Process Models Through Nonnegative Tensor Factorization [0.0]
  We introduce a novel mathematically sound method that integrates theoretical process models with interrelated minimal Hidden Markov Models. Our method consolidates: (a) theoretical process models, (b) HMMs, (c) coupled nonnegative matrix-tensor factorizations, and (d) custom model selection.
  arXiv  Detail & Related papers  (2022-10-03T16:19:27Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.