General Agents Must Learn Online

It has been widely anticipated that scaling offline training could enable artificial general intelligence (AGI) in agents with ***frozen policies***. However, such agents rely on offline knowledge, restricting their capability in big worlds that exceed their capacity. We formalize this limitation by showing frozen agents require ***a model size*** that grows with environment complexity and the accuracy demanded across rewards. Moreover, frozen agents require substantial amounts of ***training data*** to acquire this capability offline. Finally, we establish an achievable tradeoff between frozen information and ***online experience***, showing that general agents are attainable with limited persistent capacity. These results motivate architectures that integrate offline training with online experience as an alternative route toward AGI.