From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process Design

• URL: http://arxiv.org/abs/2601.06776v1
• Date: Sun, 11 Jan 2026 04:41:57 GMT
• Title: From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process Design
• Authors: Xufei Tian, Wenli Du, Shaoyi Yang, Han Hu, Hui Xin, Shifeng Qu, Ke Ye,
• Abstract summary: We propose a novel multi-agent workflow that enables iterative interactions with chemical process simulation software.<n>Our approach integrates four specialized agents responsible for task understanding, topology generation, parameter configuration, and evaluation analysis.<n>Our method achieves a 31.1% improvement in the simulation convergence rate compared to state-of-the-art baselines and reduces the design time by 89. 0%.
• Score: 21.90369595664683
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Process simulation is a critical cornerstone of chemical engineering design. Current automated chemical design methodologies focus mainly on various representations of process flow diagrams. However, transforming these diagrams into executable simulation flowsheets remains a time-consuming and labor-intensive endeavor, requiring extensive manual parameter configuration within simulation software. In this work, we propose a novel multi-agent workflow that leverages the semantic understanding capabilities of large language models(LLMs) and enables iterative interactions with chemical process simulation software, achieving end-to-end automated simulation from textual process specifications to computationally validated software configurations for design enhancement. Our approach integrates four specialized agents responsible for task understanding, topology generation, parameter configuration, and evaluation analysis, respectively, coupled with Enhanced Monte Carlo Tree Search to accurately interpret semantics and robustly generate configurations. Evaluated on Simona, a large-scale process description dataset, our method achieves a 31.1% improvement in the simulation convergence rate compared to state-of-the-art baselines and reduces the design time by 89. 0% compared to the expert manual design. This work demonstrates the potential of AI-assisted chemical process design, which bridges the gap between conceptual design and practical implementation. Our workflow is applicable to diverse process-oriented industries, including pharmaceuticals, petrochemicals, food processing, and manufacturing, offering a generalizable solution for automated process design.

Related papers

• CeProAgents: A Hierarchical Agents System for Automated Chemical Process Development [73.33844908703799]
  CeProAgents is a hierarchical multi-agent system designed to automate the development of chemical process through collaborative division of labor.<n>To rigorously evaluate the system, we establish CeProBench, a multi-dimensional benchmark structured around three core pillars of chemical engineering.
  arXiv  Detail & Related papers  (2026-03-02T09:37:18Z)
• Large Language Model Agent for User-friendly Chemical Process Simulations [0.0]
  A large language model (LLM) agent is integrated with AVEVA Process Model Protocol (MCP), allowing natural language simulations.<n>Two case studies assess the framework across different task complexities and interaction modes.<n>The framework benefits both educational purposes, by translating technical concepts and demonstrating, and experienced practitioners by automating data extraction, speeding routine tasks, and supporting.<n>While current limitations such as oversimplification, calculation errors, and technical hiccups mean expert oversight is still needed, the framework suggests LLM-based agents can become valuable collaborators.
  arXiv  Detail & Related papers  (2026-01-15T12:18:45Z)
• When AI Bends Metal: AI-Assisted Optimization of Design Parameters in Sheet Metal Forming [0.4347560796121297]
  This paper presents an AI-assisted workflow that reduces expert involvement in parameter optimization through the use of Bayesian optimization.<n>A deep learning model provides an initial parameter estimate, from which the optimization cycle iteratively refines the design until a termination condition is met.<n>We demonstrate our approach, based on a sheet metal forming process, and show how it enables us to accelerate the exploration of the design space while reducing the need for expert involvement.
  arXiv  Detail & Related papers  (2025-11-27T10:31:24Z)
• AnaFlow: Agentic LLM-based Workflow for Reasoning-Driven Explainable and Sample-Efficient Analog Circuit Sizing [1.2617078020344616]
  A novel agentic AI framework for sample-efficient and explainable analog circuit sizing is presented.<n>The AnaFlow framework is demonstrated for two circuits of varying complexity and is able to complete the sizing task fully automatically.<n>The inherent explainability makes this a powerful tool for analog design space exploration and a new paradigm in analog EDA.
  arXiv  Detail & Related papers  (2025-11-05T18:24:01Z)
• ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data [53.78763789036172]
  We present ChemActor, a fully fine-tuned large language model (LLM) as a chemical executor to convert between unstructured experimental procedures and structured action sequences.<n>This framework integrates a data selection module that selects data based on distribution divergence, with a general-purpose LLM, to generate machine-executable actions from a single molecule input.<n>Experiments on reaction-to-description (R2D) and description-to-action (D2A) tasks demonstrate that ChemActor achieves state-of-the-art performance, outperforming the baseline model by 10%.
  arXiv  Detail & Related papers  (2025-06-30T05:11:19Z)
• AutoChemSchematic AI: Agentic Physics-Aware Automation for Chemical Manufacturing Scale-Up [2.5875933818780363]
  Current AI systems cannot yet reliably generate critical engineering schematics.<n>We present a closed-loop, physics-aware framework for automated generation of industrially viable PFDs and PIDs.<n>We show that our framework generates simulator-validated process descriptions with high fidelity.
  arXiv  Detail & Related papers  (2025-05-30T13:32:00Z)
• An LLM-enabled Multi-Agent Autonomous Mechatronics Design Framework [49.633199780510864]
  This work proposes a multi-agent autonomous mechatronics design framework, integrating expertise across mechanical design, optimization, electronics, and software engineering.<n> operating primarily through a language-driven workflow, the framework incorporates structured human feedback to ensure robust performance under real-world constraints.<n>A fully functional autonomous vessel was developed with optimized propulsion, cost-effective electronics, and advanced control.
  arXiv  Detail & Related papers  (2025-04-20T16:57:45Z)
• Transfer learning for process design with reinforcement learning [3.3084327202914476]
  We propose to utilize transfer learning for process design with RL in combination with rigorous simulation methods. transfer learning is an established approach from machine learning that stores knowledge gained while solving one problem and reuses this information on a different target domain. Our results show that transfer learning enables RL to economically design feasible flowsheets with DWSIM, resulting in a flowsheet with an 8% higher revenue.
  arXiv  Detail & Related papers  (2023-02-07T10:31:14Z)
• Automated Evolutionary Approach for the Design of Composite Machine Learning Pipelines [48.7576911714538]
  The proposed approach is aimed to automate the design of composite machine learning pipelines. It designs the pipelines with a customizable graph-based structure, analyzes the obtained results, and reproduces them. The software implementation on this approach is presented as an open-source framework.
  arXiv  Detail & Related papers  (2021-06-26T23:19:06Z)
• QuaSiMo: A Composable Library to Program Hybrid Workflows for Quantum Simulation [48.341084094844746]
  We present a composable design scheme for the development of hybrid quantum/classical algorithms and for applications of quantum simulation. We implement our design scheme using the hardware-agnostic programming language QCOR into the QuaSiMo library.
  arXiv  Detail & Related papers  (2021-05-17T16:17:57Z)
• Composable Programming of Hybrid Workflows for Quantum Simulation [48.341084094844746]
  We present a composable design scheme for the development of hybrid quantum/classical algorithms and for applications of quantum simulation. We implement our design scheme using the hardware-agnostic programming language QCOR into the QuaSiMo library.
  arXiv  Detail & Related papers  (2021-01-20T14:20:14Z)

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.