AI RESEARCH
From Prompts to Worlds: How Users Iterate, Explore, and Make Sense of AI-Generated 3D Environments
arXiv CS.AI
•
ArXi:2603.13233v1 Announce Type: cross Text-to-3D generative AI systems create navigable environments from natural language prompts, but unlike text-to-image generation, evaluation requires embodied exploration of spatial coherence, scale, and navigability. We present the first empirical study of a commercial text-to-3D platform, combining think-aloud protocols, behavioral observation, and validated measures of usability, presence, and engagement. We report three findings.