Darwin Mobile Agent: A Roadmap for Self-Evolution
This work provides a practical infrastructure and conceptual roadmap for developing self-evolving GUI agents, addressing the data-collection bottleneck in real-world mobile interactions.
The authors argue that the most effective path toward general AI is to remove human priors and let intelligence emerge through interaction with a complex world, using mobile GUI as a proxy. They introduce Darwin Mobile Agent, an open-source infrastructure for autonomous reinforcement learning in mobile GUI environments, and validate its stability and scalability for policy optimization.
The goal of artificial intelligence is to create agents capable of general, adaptive behaviour in open-ended environments. Guided by the "Bitter Lesson", we argue that the most effective path toward this goal is to systematically remove human priors and allow intelligence to naturally emerge through interaction with a "Big World" that is orders of magnitude more complex than the agent itself. We propose the mobile Graphical User Interface (GUI) as a practical proxy for such a world and introduce Darwin Mobile Agent, an open-source infrastructure designed as a foundation for autonomous reinforcement learning in this domain. This framework addresses the data-collection bottleneck in real-world mobile interactions by using an asynchronous agent-environment loop across parallel cloud-phone instances. We further propose a conceptual roadmap to systematically remove human priors from three fundamental pillars of a self-evolving agent: task curricula, outcome verification, and memory management. We validate that the Darwin infrastructure provides the stability and scalability required for the first stage of this roadmap: policy optimisation in the GUI domain. This work establishes the practical and theoretical foundation necessary to move toward truly autonomous, self-evolving GUI agents.