---
title: "代码世界模型：将编码智能体作为世界大脑，实现持久化世界演化"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.25927v1"
permalink: "https://feed.astralor.com/items/itm_d3796f7ce60b690e19bc9e0d"
published: "2026-08-26T15:37:33.000Z"
score: 77
channel: "tech"
tags: ["MiniMax-H3","世界模型","代理表示","编码智能体","视频生成"]
---

# 代码世界模型：将编码智能体作为世界大脑，实现持久化世界演化

## AI 点评

> 这篇论文最值得关注的点是把代码当持久记忆，让视频模型只做渲染，解决了我一直觉得世界模型像‘近视眼’的问题——只看画面猜不到规则。对研究开放世界模拟和具身智能的朋友来说，这个框架值得细读。

## 速览

现有视频世界模型主要从视觉观察中学习动态，难以维持持久后果并支持连贯的开放式演化。本文提出代码世界模型（Code World Model），将世界演化与视觉呈现分离：编码智能体作为世界大脑，推理事件及其后果并生成可执行代码以维持持久状态，通过代理表示将时空约束编译成代理视频，驱动视频模型生成高保真观察。在游戏数据上微调后，MiniMax-H3 能遵循基于代理的时空规范，展示结合代码与视频模型实现开放世界模型的潜力。

## 关键点

- 提出代码世界模型框架，由编码智能体负责持久化世界状态与规则一致演化
- 引入代理表示连接可执行状态与视频生成，将时空约束编译为代理视频
- 构建游戏与真实视频的代理-观察对齐数据管道，微调 MiniMax-H3 实现遵循代理规范的视频渲染
- 展示了代码与视频模型结合用于开放式世界模型的新路径

## 全文

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.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_d3796f7ce60b690e19bc9e0d