Abstract
This paper explores the potential of using Large Language Models (LLMs) to generate Business Process Model and Notation (BPMN) files as input for Robotic Process Automation (RPA) tools. The combination of AI-driven workflow generation with RPA aims to improve the automation of complex processes in both scientific and business domains. The proposed approach leverages the ability of LLMs to interpret natural language instructions and convert them into structured BPMN files, which can then be graphically edited using software like Camunda and executed by RPA tools. The feasibility of this approach is demonstrated through zero-shot prompt experiments using Anthropic Claude 3 Opus and GPT-4o. This solution has the potential to streamline the automation of workflows, reduce human error, and increase productivity across various industries.
Cite this work
Carlos Toxtli-Hernández and Wangfan Li. 2024. Automating Automation: Using LLMs to Generate BPMN Workflows for Robotic Process Automation. Artificial Intelligence and Applications (ICAI'24), CSCE 2024. Communications in Computer and Information Science, vol. 2252. Springer, Cham.. https://doi.org/10.1007/978-3-031-86623-4_18
@misc{Toxtli2024Automating,
doi = {10.13140/RG.2.2.25996.12165},
url = {https://www.researchgate.net/doi/10.13140/RG.2.2.25996.12165},
author = {Toxtli, Carlos and {Wangfan Li}},
language = {en},
title = {Automating Automation: Using LLMs to Generate BPMN Workflows for Robotic Process Automation},
publisher = {Unpublished},
year = {2024},
howpublished = {Preprint, ResearchGate},
note = {Preprint}
}
