World Models Should Prioritize the Unification of Physical and Social Dynamics

Xiaoyuan Zhang, Chengdong Ma, Yizhe Huang, Weidong Huang, Siyuan Qi, Song-Chun Zhu, Xue Feng, Yaodong Yang

Keywords: World Model

Abstract: World models, which explicitly learn environmental dynamics to lay the foundation for planning, reasoning, and decision-making, are rapidly advancing in predicting both physical dynamics and aspects of social behavior, yet predominantly in separate silos. This division results in a systemic failure to model the crucial interplay between physical environments and social constructs, rendering current models fundamentally incapable of adequately addressing the true complexity of real-world systems where physical and social realities are inextricably intertwined. This position paper argues that the systematic, bidirectional unification of physical and social predictive capabilities is the next crucial frontier for world model development. We contend that comprehensive world models must holistically integrate objective physical laws with the subjective, evolving, and context-dependent nature of social dynamics. Such unification is paramount for AI to robustly navigate complex real-world challenges and achieve more generalizable intelligence. This paper substantiates this imperative by analyzing core impediments to integration, proposing foundational guiding principles (ACE Principles), and outlining a conceptual framework alongside a research roadmap towards truly holistic world models.

Lay Summary: World models are AI systems that learn how the environment operates to support planning, reasoning, and decision-making. Recent advances have enabled them to predict both physical dynamics, such as how objects move, and social behavior, such as how people interact. Yet most approaches study these two domains separately. This separation prevents AI from understanding the real world, where the physical and social domains are tightly entangled. This paper argues that bringing these two predictive abilities together is the next essential step for world model research. We propose that a comprehensive world model should integrate the objective rules that govern the physical world with the subjective, evolving, and context-dependent nature of social behavior. Such integration would allow AI systems to better navigate complex environments that involve both physical actions and human interactions. We identify key obstacles to this unification, introduce guiding principles called the ACE Principles, and outline a research roadmap toward truly holistic world models that combine physical precision with social understanding.

Submission Number: 105