PlayWorld Puts Multi-Modal 'Agent Players' Inside World Models Across 171 Scenarios — and Finds Long-Horizon State Persistence Still Broken

arXiv (via HuggingFace Daily Papers)·low signalXBlueskyLinkedInCopy link

Kaixin Ding, Hengshuang Zhao and colleagues released PlayWorld on August 13 (arXiv 2608.13552), a benchmark of 171 objective-driven scenarios evaluated on geometry consistency, interaction fidelity, out-of-sight evolution and insight evolution. The methodological fix is replacing fixed action-conditioned evaluation — which made cross-model comparison unfair — with multi-modal agent players that interact with each world model on its own terms. Headline finding: current models remain unreliable on long-horizon interactive objectives, particularly spatial consistency and persistent state evolution. Code and data are public.