Coordinating two players in a cooking task requires a vision-language agent to track changing scene states, sequence recipe steps, and allocate shared resources under a time budget. We introduce an Overcooked-inspired benchmark for evaluating these capabilities in Unreal Engine environments constructed using coding age...
Zi-Yi Jiao, Heng Zhang, Drishti Regmi et al.· 0 citations
SceneBloom is introduced, an agentic framework that combines visual layout sampling with contract-guided 3D compilation that attains the highest visual quality and physical stability among the compared methods and is the only method with no detected mesh collisions and out-of-bounds objects.
This work introduces Code4Scene, a benchmark of 190 Unreal Engine cases built from human-assembled scenes that evaluates coding agents on two complementary settings under a shared execution interface, and exposes a gap between plausible 3D generation and reliable spatial reasoning and state control.
Xiao-Kang Ye, Siddhant Hitesh Mantri, Zi-Meng Chen et al.· arXiv.org· 3 citations
Unified Latent Diffusion Reasoner improves multimodal reasoning by weaving it into a single thread, where the model predicts successive thoughts in a common representation space.