网络世界模型

摘要

语言智能体日益需要能在其中行动、记忆和学习的持久化世界。现有方法处于两个极端：传统Web框架提供由数据库支持的可靠但固定的上下文，而完全生成式世界模型以牺牲可控性和工程可实现性为代价追求无限环境。本研究提出网络世界模型（WWM）作为折中方案——通过普通网页代码实现世界状态与"物理规则"以确保逻辑一致性，同时由大语言模型基于这种结构化潜状态生成上下文、叙事和高层决策。我们在真实网络技术栈上构建了系列WWM系统，包括基于真实地理的无限旅行图册、虚构星系探索器、网络级百科全书式叙事世界，以及模拟与游戏化环境。通过这些系统，我们总结出WWM的实用设计原则：分离代码定义的规则与模型驱动的想象，将潜状态表示为类型化网络接口，利用确定性生成实现无限但有结构的探索。研究表明，网络技术栈本身可作为世界模型的可扩展基础，实现可控且开放的环境。项目页面：https://github.com/Princeton-AI2-Lab/Web-World-Models。

English

Language agents increasingly require persistent worlds in which they can act, remember, and learn. Existing approaches sit at two extremes: conventional web frameworks provide reliable but fixed contexts backed by databases, while fully generative world models aim for unlimited environments at the expense of controllability and practical engineering. In this work, we introduce the Web World Model (WWM), a middle ground where world state and ``physics'' are implemented in ordinary web code to ensure logical consistency, while large language models generate context, narratives, and high-level decisions on top of this structured latent state. We build a suite of WWMs on a realistic web stack, including an infinite travel atlas grounded in real geography, fictional galaxy explorers, web-scale encyclopedic and narrative worlds, and simulation- and game-like environments. Across these systems, we identify practical design principles for WWMs: separating code-defined rules from model-driven imagination, representing latent state as typed web interfaces, and utilizing deterministic generation to achieve unlimited but structured exploration. Our results suggest that web stacks themselves can serve as a scalable substrate for world models, enabling controllable yet open-ended environments. Project Page: https://github.com/Princeton-AI2-Lab/Web-World-Models.

网络世界模型

Web World Models

摘要

Support