程式碼世界模型：作為世界大腦的程式設計智能體

摘要

世界模型旨在模擬複雜環境在動作與事件作用下的演化方式，然而現有的基於視頻的世界模型主要從視覺觀測中學習動力學——視覺觀測只能呈現結果，而非支配世界演化的底層知識、規則與機制。這使得模型難以維持持續性的後果，也難以支持連貫且開放式的演化。我們提出「程式世界模型」（Code World Model），這是一個將世界演化與視覺實現分離的框架，透過結合語言模型的推理與編碼能力以及視頻模型的生成先驗來達成。編碼智能體充當世界大腦，負責推理事件及其後果，並生成可執行的程式碼以維持持久的世界狀態並執行符合規則的演化。為了將可執行的狀態與視覺生成相連接，我們引入了一種代理表示，該表示編碼了逐幀的時空約束，並被編譯為代理視頻，進而引導視頻模型渲染高保真的視覺觀測結果。我們進一步開發了數據管線，用於從遊戲實況與真實世界視頻中建構對齊的代理-觀測對。在配對的遊戲數據上進行微調後，MiniMax-H3 能夠遵循由編碼智能體所構建的簡單互動世界中的代理式時空規範，同時保留豐富的視覺細節與動力學特性。這些結果展示了將程式碼用於持久世界演化、將視頻模型用於靈活視覺實現的潛力，為邁向開放式世界模型開闢了新的路徑。

English

World models aim to simulate how complex environments evolve under actions and events, yet existing video-based world models primarily learn dynamics from visual observations, which reveal outcomes rather than the underlying knowledge, rules, and mechanisms governing world evolution. This makes it difficult to maintain persistent consequences and support coherent, open-ended evolution. We introduce Code World Model, a framework that separates world evolution from visual realization by combining the reasoning and coding capabilities of language models with the generative priors of video models. A coding agent serves as the world brain, reasoning about events and their consequences and generating executable code to maintain persistent world state and perform rule-consistent evolution. To connect executable state with visual generation, we introduce a proxy representation that encodes frame-wise spatiotemporal constraints and is compiled into a proxy video, which conditions a video model to render high-fidelity visual observations. We further develop data pipelines for constructing aligned proxy-observation pairs from gameplay and real-world videos. After fine-tuning on paired gameplay data, MiniMax-H3 follows proxy-based spatiotemporal specifications from simple interactive worlds built by the coding agent while preserving rich visual details and dynamics. These results demonstrate the potential of combining code for persistent world evolution with video models for flexible visual realization, providing a new path toward open-ended world models.