The field of Human-Computer Interaction (HCI) is witnessing significant advancements in GUI automation, with a focus on developing intelligent agents that can interact with complex digital workspaces. Researchers are exploring innovative approaches to integrate biomechanics and cognitive models to enable more accurate simulations of user behavior. Reinforcement learning is being leveraged to improve agent performance in dynamic interactive GUI environments, with curriculum learning frameworks being proposed to address the limitations of traditional RL methods. Noteworthy papers in this area include: CRAFT-GUI, which achieves significant improvements over previous state-of-the-art approaches in GUI interaction tasks. ComputerRL, which introduces a framework for autonomous desktop intelligence that enables agents to operate complex digital workspaces skillfully.