Human Cognition in Machines: A Unified Perspective of World Models
For researchers in AI and cognitive science, this provides a comprehensive taxonomy and identifies gaps in world model research, but it is primarily a survey and conceptual framework without empirical results.
This paper presents a unified framework for world models grounded in Cognitive Architecture Theory, identifying that motivation and meta-cognition are under-researched. It introduces Epistemic World Models for scientific discovery and proposes research directions using active inference and global workspace theory.
This comprehensive report distinguishes prior works by the cognitive functions they innovate. Many works claim an almost "human-like" cognitive capability in their world models. To evaluate these claims requires a proper grounding in first principles in Cognitive Architecture Theory (CAT). We present a conceptual unified framework for world models that fully incorporates all the cognitive functions associated with CAT (i.e. memory, perception, language, reasoning, imagining, motivation, and meta-cognition) and identify gaps in the research as a guide for future states of the art. In particular, we find that motivation (especially intrinsic motivation) and meta-cognition remain drastically under-researched, and we propose concrete directions informed by active inference and global workspace theory to address them. We further introduce Epistemic World Models, a new category encompassing agent frameworks for scientific discovery that operate over structured knowledge. Our taxonomy, applied across video, embodied, and epistemic world models, suggests research directions where prior taxonomies have not.