Open Computer Agent

Qwen2.5-VL is the latest vision-language model from the Qwen series, representing a significant advancement over its predecessor, Qwen2-VL. This model excels in visual understanding, capable of recognizing a wide array of objects, including text, charts, icons, graphics, and layouts within images. It functions as a visual agent, capable of reasoning and dynamically directing tools, enabling applications such as computer and phone usage. Qwen2.5-VL can comprehend videos exceeding one hour in length and can pinpoint relevant segments within them. Additionally, it accurately localizes objects in images by generating bounding boxes or points and provides stable JSON outputs for coordinates and attributes. The model also supports structured outputs for data like scanned invoices, forms, and tables, benefiting sectors such as finance and commerce. Available in base and instruct versions across 3B, 7B, and 72B sizes, Qwen2.5-VL is accessible through platforms like Hugging Face and ModelScope.

Introducing the Gemini 2.5 Computer Use model, a specialized agent model built on top of Gemini 2.5 Pro’s visual reasoning capabilities, designed to interact directly with user interfaces (UIs). It is exposed via a new computer-use tool in the Gemini API, with inputs that include the user’s request, a screenshot of the UI environment, and a history of recent actions. The model generates function calls corresponding to UI actions like clicking, typing, or selecting, and may request user confirmation for higher-risk tasks. After each action is executed, a new screenshot and URL are fed back into the model to continue the loop until the task completes or is halted. It is optimized primarily for web browser control and shows promise for mobile UI interaction, though it is not yet suited for desktop OS-level control. In benchmarks across web and mobile control tasks, Gemini 2.5 Computer Use outperforms leading alternatives, delivering high accuracy at lower latency.