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.

Agent S2 is an open, modular, and scalable framework for computer-use agents developed by Simular. These autonomous AI agents interact directly with graphical user interfaces (GUIs) on desktops, mobile devices, browsers, and various software applications, mimicking human-like control via mouse and keyboard. Building upon the initial Agent S framework, Agent S2 enhances performance and modularity by integrating both frontier foundation models and specialized models. It achieves state-of-the-art results, notably surpassing previous benchmarks on OSWorld and AndroidWorld evaluations. Key design principles include proactive hierarchical planning, where the agent dynamically updates its plans after each subtask; visual grounding for precise GUI interaction using raw screenshots; an improved Agent-Computer Interface (ACI) that delegates complex tasks to specialized modules; and an agentic memory mechanism that enables continual learning from experience.