AppAgentX: Evolving GUI Agents as Proficient Smartphone Users
This work addresses the problem of slow GUI automation for smartphone users by combining the intelligence of LLM-based agents with the efficiency of rule-based systems, though it is incremental in nature.
The paper tackles the inefficiency of LLM-based GUI agents in routine tasks by proposing an evolutionary framework that uses memory to identify and replace repetitive action sequences with high-level shortcuts, resulting in significant improvements in efficiency and accuracy on benchmark tasks.
Recent advancements in Large Language Models (LLMs) have led to the development of intelligent LLM-based agents capable of interacting with graphical user interfaces (GUIs). These agents demonstrate strong reasoning and adaptability, enabling them to perform complex tasks that traditionally required predefined rules. However, the reliance on step-by-step reasoning in LLM-based agents often results in inefficiencies, particularly for routine tasks. In contrast, traditional rule-based systems excel in efficiency but lack the intelligence and flexibility to adapt to novel scenarios. To address this challenge, we propose a novel evolutionary framework for GUI agents that enhances operational efficiency while retaining intelligence and flexibility. Our approach incorporates a memory mechanism that records the agent's task execution history. By analyzing this history, the agent identifies repetitive action sequences and evolves high-level actions that act as shortcuts, replacing these low-level operations and improving efficiency. This allows the agent to focus on tasks requiring more complex reasoning, while simplifying routine actions. Experimental results on multiple benchmark tasks demonstrate that our approach significantly outperforms existing methods in both efficiency and accuracy. The code will be open-sourced to support further research.