Simular Integrations

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.