Research & Papers

Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning

Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning

Deep Dive

Computer Science > Computer Vision and Pattern Recognition arXiv:2608.27549 (cs) [Submitted on 27 Aug 2026] Title: Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning Authors: Hanyang Wang , Yimo Cai , Weiliang Chen , Jiawei Chi , Haowen Sun , Qiyu Dai , Yi-H

📬 Get the top 10 AI stories daily