arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2601.15533cs.AI
收藏

从生成引擎到可操作模拟器:世界模型中物理基础的必要性

From Generative Engines to Actionable Simulators: The Imperative of Physical Grounding in World Models

Zhikang Chen, Tingting Zhu

AI总结:

本文提出将世界模型重新定义为可操作模拟器,强调因果结构和约束意识,以提升医疗决策中的反事实推理和长期预见能力。

摘要:

世界模型是一种人工智能系统,能够模拟环境在动作作用下如何演变,从而通过想象的未来进行规划,而非被动感知。然而,当前的世界模型却存在视觉混淆:错误地认为高保真视频生成意味着对物理和因果动态的理解。我们证明,尽管现代模型在预测像素方面表现出色,但它们经常违反不变约束,无法应对干预,并在安全关键的决策中崩溃。本文调查认为,视觉真实感是世界理解的不可靠代理。相反,有效的世界模型必须编码因果结构,尊重领域特定约束,并在长期内保持稳定。我们提出将世界模型重新定义为可操作模拟器,而非视觉引擎,强调结构化的四维接口、约束意识的动力学和闭环评估。通过医疗决策制定作为知识压力测试,其中试错是不可能的,错误是不可逆的,我们证明世界模型的价值不在于其模拟的现实程度,而在于其支持反事实推理、干预规划和稳健的长周期预见能力。

英文摘要:

A world model is an AI system that simulates how an environment evolves under actions, enabling planning through imagined futures rather than reactive perception. Current world models, however, suffer from visual conflation: the mistaken assumption that high-fidelity video generation implies an understanding of physical and causal dynamics. We show that while modern models excel at predicting pixels, they frequently violate invariant constraints, fail under intervention, and break down in safety-critical decision-making. This survey argues that visual realism is an unreliable proxy for world understanding. Instead, effective world models must encode causal structure, respect domain-specific constraints, and remain stable over long horizons. We propose a reframing of world models as actionable simulators rather than visual engines, emphasizing structured 4D interfaces, constraint-aware dynamics, and closed-loop evaluation. Using medical decision-making as an epistemic stress test, where trial-and-error is impossible and errors are irreversible, we demonstrate that a world model's value is determined not by how realistic its rollouts appear, but by its ability to support counterfactual reasoning, intervention planning, and robust long-horizon foresight.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑