The Training World Kept Its Rules While Its Pictures Changed

AgentGarten separates world rules from visual observation. Simulators and game engines maintain persistent state and program-defined interactions, while a shared neural renderer turns structured conditions into real-time views. The renderer is adapted from a video model, distilled with a method that backpropagates through replayed history, and optimized for interactive latency. Agents then distill rounds of experience into inherited playbooks. In the authors' study, agents learned with four rounds where a conventional reinforcement-learning comparator used millions. That comparison is specific to the constructed environments and learning protocol; the framework's durable idea is that new practice worlds can be written as code without rebuilding the visual stack each time.