Code-as-World：通过可执行世界表示实现智能体物理推理
原标题：Paper page - Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning
AI 摘要
Hugging Face 论文页面介绍了 Code-as-World 范式，该范式将物理环境表示为可执行代码，以支持视觉语言模型的定量推理和可扩展监督。研究团队开发了一种基于溯因推理的智能体发现循环，通过提出、执行、渲染、验证和迭代细化可执行世界假设，从多模态观测中构建世界表示。实验表明，Code-as-World-VL 在 QuantiPhy 基准上达到最先进性能，并超越领先的专有模型，凸显了可执行世界表示作为物理智能可扩展基础的潜力。
正文节选
Code as Worlds: Agentic Discovery of Executable World Representations for Physical Reasoning Abstract Code-as-World represents physical environments as executable code to enable quantitative reasoning and scalable supervision for vision-language models. Physical understanding and reasoning depend on forming compact and generalizable representations of the world. While modern vision-language models can recognize and explain diverse physical events, they often lack explicit representations of the