Critiques of World Models

2025-07-07

AI Summary

Current world model research predominantly emphasizes perceptual prediction while neglecting the simulation of actionable possibilities—a critical limitation for goal-directed agency. Method: Inspired by the imaginative mechanisms in *Dune* and psychological theories of hypothetical thinking, we propose a novel paradigm centered on simulating *all physically feasible actions* in reality. We design a hierarchical, multi-scale, continuous-discrete hybrid world model architecture that enforces physical consistency, autonomous dynamical evolution, and nested cognitive structure to support purposeful reasoning and action. Our approach integrates generative modeling, self-supervised learning, and hypothetical reasoning. Contribution/Results: This work establishes the first theoretical framework and PAN (Physical, Autonomous, Nested) AGI system blueprint explicitly targeting *actionable simulation*. It advances world models from passive perception-based prediction toward active, cognition-driven modeling—constituting a foundational shift toward general artificial intelligence.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Multiagent Systems: Agent-Based Simulation and Emergent Behavior
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Search and Retrieval-Augmented AI: Agentic search

Abstract

World Model, the supposed algorithmic surrogate of the real-world environment which biological agents experience with and act upon, has been an emerging topic in recent years because of the rising needs to develop virtual agents with artificial (general) intelligence. There has been much debate on what a world model really is, how to build it, how to use it, and how to evaluate it. In this essay, starting from the imagination in the famed Sci-Fi classic Dune, and drawing inspiration from the concept of "hypothetical thinking" in psychology literature, we offer critiques of several schools of thoughts on world modeling, and argue the primary goal of a world model to be simulating all actionable possibilities of the real world for purposeful reasoning and acting. Building on the critiques, we propose a new architecture for a general-purpose world model, based on hierarchical, multi-level, and mixed continuous/discrete representations, and a generative and self-supervision learning framework, with an outlook of a Physical, Agentic, and Nested (PAN) AGI system enabled by such a model.

Problem

• Defining and conceptualizing World Models for AGI
• Critiquing existing approaches to building World Models
• Proposing a new hierarchical architecture for World Models

Innovation

• Hierarchical multi-level mixed representations for world modeling
• Generative self-supervised learning framework implementation
• PAN AGI system enabling physical agentic nested intelligence