The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use

ShowLab, National University of Singapore

Game (Honkai: Star Rail)

Claude 3.5 Computer Use can help complete Honkai: Star Rail daily tasks, accurately locating and interacting with in-game elements.

We can also automate warping (gacha pulls) in the game using Claude 3.5 Computer Use—and even get pretty lucky while we're at it! 🥳

Office (Presentation + Spreadsheets)

Claude 3.5 Computer Use can help complete office software tasks, observe and generate correct plans, and accurately execute the plan actions, showcasing its strong planning, action and critic capabilities.

Claude 3.5 Computer Use can streamline the entire GUI task, from opening the target application, navigating in the webpage, to performing actions that are tailored to the task at hand.

Steps during task execution

We can also visualize the steps during task execution, including each GUI state and the reasoning from the model.

Loading...
🤖 Claude 3.5 Computer Use: Message will appear here.

Abstract

The recently released model, Claude 3.5 Computer Use, stands out as the first frontier AI model to offer computer use in public beta as a graphical user interface (GUI) agent. As an early beta, its capability in the real-world complex environment remains unknown.

In this case study to explore Claude 3.5 Computer Use, we curate and organize a collection of carefully designed tasks spanning a variety of domains and software. Observations from these cases demonstrate Claude 3.5 Computer Use's unprecedented ability in end-to-end language to desktop actions. Along with this study, we provide an out-of-the-box agent framework for deploying API-based GUI automation models with easy implementation.

Our case studies aim to showcase a groundwork of capabilities and limitations of Claude 3.5 Computer Use with detailed analyses and bring to the fore questions about planning, action, and critic which must be considered for future improvement. We hope this preliminary exploration will inspire future research into the GUI agent community.

Remotely automate your computer with Claude 3.5 Computer Use and Computer Use OOTB🦾

Computer Use OOTB is a out-of-the-box, cross-platform framework for deploying API-based GUI automation models on your computer with ease, no configuration needed.

BibTeX

@article{hu2024dawn,
  author    = {Siyuan Hu and Mingyu Ouyang and Difei Gao and Mike Zheng Shou},
  title     = {The Dawn of GUI Agent: A Preliminary Case Study with Claude 3.5 Computer Use},
  year      = {2024},
}