AI RESEARCH
AutoRPA: Efficient GUI Automation through LLM-Driven Code Synthesis from Interactions
arXiv CS.AI
•
ArXi:2605.21082v1 Announce Type: new Large Language Model (LLM) based agents have nstrated proficiency in multi-step interactions with graphical user interfaces (GUIs). While most research focuses on improving single-task performance, practical scenarios often involve repetitive GUI tasks for which invoking LLM reasoning repeatedly, i.e., the ReAct paradigm, is inefficient. Prior to LLMs, traditional Robotic Process Automation (RPA) offers runtime efficiency but demands significant manual effort to develop and maintain.