Quo Vadis, World Modeling?

世界模型，何去何从？

Continually improving agents require dynamic interaction feedback beyond static supervision, yet direct real-environment interaction is costly, slow, unsafe, and hard to parallelize. World modeling offers a natural intermediate proxy that allows agents to query lower-cost, more controllable feedback before committing to real actions. 持续进化的智能体需要超越静态监督的动态交互反馈，然而直接在真实环境中进行交互既昂贵、缓慢、不安全，也难以并行化。世界模型提供了一种自然的中间代理，允许智能体在执行真实动作之前，查询成本更低、更可控的反馈。

Classical world models instantiate this proxy primarily through future physical-state prediction, a formulation useful yet narrow for agents that require actionable feedback beyond raw state transitions. In this work, we conceptualize Agent-Centric Interactive World Proxies, shifting the fundamental paradigm from physical state transitions to agent-usable information transitions, such as execution outcomes, retrieved experiences or skills, and verification signals, broadening the scope of world modeling to provide versatile feedback for continually improving agents. 经典的世界模型主要通过预测未来物理状态来实现这种代理，这种范式虽然有用，但对于需要超越原始状态转换、获取可操作反馈的智能体来说过于狭窄。在这项工作中，我们提出了“以智能体为中心的交互式世界代理”概念，将基本范式从物理状态转换转向智能体可用的信息转换，例如执行结果、检索到的经验或技能以及验证信号，从而拓宽了世界模型的范畴，为持续进化的智能体提供多功能的反馈。

To systematically map this design space, we organize world proxies into six functional forms based on their feedback modalities: dynamics, spatial, execution, memory/experience, skill, and reward/verification proxies, which together characterize the primary ways world modeling serves agent improvement. 为了系统地映射这一设计空间，我们根据反馈模态将世界代理组织为六种功能形式：动力学、空间、执行、记忆/经验、技能以及奖励/验证代理，它们共同刻画了世界模型服务于智能体进化的主要方式。

We further analyze how these proxies empower agents across three progressive levels: L.1 Inference-Time Guidance, where proxy outputs enrich in-context information for superior decisions; L.2 Training-Time Optimization, where proxy outputs yield rewards, critiques, or synthetic rollouts for policy learning; and L.3 Agent-Proxy Co-Evolution, where real-environment evidence continuously updates both the proxy and the agent for co-evolution. 我们进一步分析了这些代理如何在三个递进的层级上赋能智能体：L.1 推理时引导（Inference-Time Guidance），即代理输出丰富上下文信息以辅助做出更优决策；L.2 训练时优化（Training-Time Optimization），即代理输出为策略学习提供奖励、评价或合成轨迹；以及 L.3 智能体-代理协同进化（Agent-Proxy Co-Evolution），即真实环境的证据不断更新代理和智能体，实现共同进化。

Ultimately, this work recasts world modeling into an agent-centric paradigm, establishing a roadmap for building world proxies that empower agents to plan better, learn faster, and evolve continually. 最终，这项工作将世界模型重塑为以智能体为中心的范式，为构建能够赋能智能体实现更好规划、更快学习和持续进化的世界代理确立了路线图。