EUVIMEDEUVIMED entdecken
Crossref

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

Xufei Tian, Wenli Du, Shaoyi Yang, Han Hu, Hui Xin, Shifeng Qu, Ke Ye

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (35) · 29705-29713

DOI: 10.1609/aaai.v40i35.40215 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Xufei Tian und 6 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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.

Zitieren

APA

Tian, X., Du, W., Yang, S., Hu, H., Xin, H., Qu, S., & Ye, K. (2026). From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process Design. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29705-29713. https://doi.org/10.1609/aaai.v40i35.40215

Vancouver

Tian X, Du W, Yang S, Hu H, Xin H, Qu S, et al. From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process Design. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(35):29705-29713. doi:10.1609/aaai.v40i35.40215

BibTeX
@article{Tian2026,
  author = {Tian, Xufei and Du, Wenli and Yang, Shaoyi and Hu, Han and Xin, Hui and Qu, Shifeng and Ye, Ke},
  title = {From Text to Simulation: A Multi-Agent LLM Workflow for Automated Chemical Process Design},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {35},
  pages = {29705--29713},
  doi = {10.1609/aaai.v40i35.40215}
}
Kostenlos starten →