This paper presents a new automation paradigm, Agentic Process Automation (APA), which uses Large Language Models (LLMs) to offload human labor in both the construction and execution of tasks. The authors introduce ProAgent, an LLM-based agent that can craft workflows from human instructions and make complex decisions. The paper highlights the limitations of Robotic Process Automation (RPA) and how APA can address these issues, providing a more efficient and intelligent solution. Empirical experiments are conducted to show the feasibility of APA.
Publication date: 2 Nov 2023
Project Page: https://github.com/OpenBMB/ProAgent
Paper: https://arxiv.org/pdf/2311.10751
Leave a comment
