AgentGarten real-time interactive world framework proposed

Jiawei Chi proposes the AgentGarten framework, which couples simulators and game engines to a shared neural renderer to build real-time interactive virtual environments. The simulation backend maintains persistent world state and executes program-defined interaction rules; the renderer generates visual observations from structured conditions exported through a unified interface. The neural renderer is adapted from a pretrained video model to take geometry-conditioned input, is distilled with the proposed Adversarial Forcing, and has its inference optimized for real-time interaction. The report gives no measured results for the framework or comparisons with other approaches.

AI-written from the coverage · updated 4 h ago

Not enough continuous observations to chart a trend yet.