GPTVoiceTasker: Advancing Multi-step Mobile Task Efficiency Through Dynamic Interface Exploration and Learning
Minh Duc Vu, Han Wang, Jieshan Chen, Zhuang Li, Shengdong Zhao, Zhenchang Xing, Chunyang Chen
Abstract
Virtual assistants have the potential to play an important role in helping users achieves different tasks. However, these systems face challenges in their real-world usability, characterized by inefficiency and struggles in grasping user intentions. Leveraging recent advances in Large Language Models (LLMs), we introduce GptVoiceTasker, a virtual assistant poised to enhance user experiences and task efficiency on mobile devices. GptVoiceTasker excels at intelligently deciphering user commands and executing relevant device interactions to streamline task completion. For unprecedented tasks, GptVoiceTasker utilises the contextual information and on-screen content to continuously explore and execute the tasks. In addition, the system continually learns from historical user commands to automate subsequent task invocations, further enhancing execution efficiency. From our experiments, GptVoiceTasker achieved 84.5% accuracy in parsing human commands into executable actions and 85.7% accuracy in automating multi-step tasks. In our user study, GptVoiceTasker boosted task efficiency in real-world scenarios by 34.85%, accompanied by positive participant feedback. We made GptVoiceTasker open-source, inviting further research into LLMs utilization for diverse tasks through prompt engineering and leveraging user usage data to improve efficiency.