Automatic Macro Mining from Interaction Traces at Scale
This addresses the challenge of understanding mobile interaction and enabling task automation for users and developers, though it appears incremental as it applies LLMs to a known bottleneck in mobile app analysis.
The researchers tackled the problem of automatically extracting semantically meaningful macros (building block tasks like 'login' or 'booking a flight') from mobile interaction traces at scale, using a novel Large Language Model (LLM)-based approach that produced fully executable macros with natural language descriptions, validated through user evaluation, comparative analysis, and automatic execution.
Macros are building block tasks of our everyday smartphone activity (e.g., "login", or "booking a flight"). Effectively extracting macros is important for understanding mobile interaction and enabling task automation. These macros are however difficult to extract at scale as they can be comprised of multiple steps yet hidden within programmatic components of mobile apps. In this paper, we introduce a novel approach based on Large Language Models (LLMs) to automatically extract semantically meaningful macros from both random and user-curated mobile interaction traces. The macros produced by our approach are automatically tagged with natural language descriptions and are fully executable. We conduct multiple studies to validate the quality of extracted macros, including user evaluation, comparative analysis against human-curated tasks, and automatic execution of these macros. These experiments and analyses show the effectiveness of our approach and the usefulness of extracted macros in various downstream applications.