VideoCoCo：基于智能双引擎系统的代码即思维链物理一致视频生成

摘要

文生视频模型已取得了卓越的视觉质量，但由于场景的时间演化必须从高度压缩的文本提示中隐式推断，它们仍然难以生成物理一致的动力学。现有的思维链方法引入了中间计划或视觉状态，但这些表示通常不可执行或在时间上稀疏，限制了它们实例化和控制完整时空过程的能力。为解决这一局限性，我们提出了 VideoCoCo，一种智能体双引擎框架，其中可执行的 Blender 代码充当过程级思维链。给定文本提示，代码智能体生成一个 Blender 程序，该程序明确指定场景及其时间演化。可执行仿真引擎运行该程序以产生确定性的时空草稿，随后通过基于草稿条件的编辑，由生成式视频引擎将其转换为照片级真实感视频。这种分解将过程级推理与高保真视觉实现分离开来。为了使视频编辑器适配仿真草稿，我们构建了 VideoCoCo-3K，一个包含草稿-指令-目标三元组的精选数据集。VideoCoCo 将 OmniWeaving 基线在 PhyGenBench 上从 0.475 提升至 0.558，在 VBench-2.0 上从 52.18 提升至 77.88，在两个基准上均取得了最佳平均分数。这些结果表明，可执行代码为物理一致的视频生成提供了一种有效、可控且可检查的中间表示。

English

Text-to-video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal evolution of a scene must be inferred implicitly from a highly compressed text prompt. Existing chain-of-thought approaches introduce intermediate plans or visual states, but these representations are typically non-executable or temporally sparse, limiting their ability to instantiate and control the complete spatiotemporal process. To address this limitation, we introduce VideoCoCo, an agentic dual-engine framework in which executable Blender code serves as a process-level chain of thought. Given a text prompt, a coding agent synthesizes a Blender program that explicitly specifies the scene and its temporal evolution. The executable simulation engine runs the program to produce a deterministic spatiotemporal draft, which is subsequently transformed into a photorealistic video by a generative video engine through draft-conditioned editing. This decomposition separates process-level reasoning from high-fidelity visual realization. To adapt the video editor to simulated drafts, we construct VideoCoCo-3K, a curated dataset of draft-instruction-target triplets. VideoCoCo improves the OmniWeaving baseline from 0.475 to 0.558 on PhyGenBench and from 52.18 to 77.88 on VBench-2.0, achieving the best average score on both benchmarks. These results demonstrate that executable code provides an effective, controllable, and inspectable intermediate representation for physically consistent video generation.