ScreenAgent: A Vision Language Model-driven Computer Control Agent
This work addresses the challenge of building a generalist AI agent for assisting humans in daily digital tasks, though it appears incremental as it builds on existing VLM and LLM tool-use frameworks.
The authors tackled the problem of enabling a Vision Language Model (VLM) agent to control a computer by interacting with its graphical user interface (GUI) through mouse and keyboard actions, achieving capabilities comparable to GPT-4V with more precise UI positioning.
Existing Large Language Models (LLM) can invoke a variety of tools and APIs to complete complex tasks. The computer, as the most powerful and universal tool, could potentially be controlled directly by a trained LLM agent. Powered by the computer, we can hopefully build a more generalized agent to assist humans in various daily digital works. In this paper, we construct an environment for a Vision Language Model (VLM) agent to interact with a real computer screen. Within this environment, the agent can observe screenshots and manipulate the Graphics User Interface (GUI) by outputting mouse and keyboard actions. We also design an automated control pipeline that includes planning, acting, and reflecting phases, guiding the agent to continuously interact with the environment and complete multi-step tasks. Additionally, we construct the ScreenAgent Dataset, which collects screenshots and action sequences when completing a variety of daily computer tasks. Finally, we trained a model, ScreenAgent, which achieved computer control capabilities comparable to GPT-4V and demonstrated more precise UI positioning capabilities. Our attempts could inspire further research on building a generalist LLM agent. The code is available at \url{https://github.com/niuzaisheng/ScreenAgent}.