Research on World Models Is Not Merely Injecting World Knowledge into Specific Tasks

TL;DR

This paper critiques current fragmented approaches to world models in AI and proposes a unified, normative framework that integrates interaction, perception, reasoning, and spatial understanding for more robust and general models.

Contribution

It introduces a comprehensive design specification for world models, moving beyond task-specific methods towards a unified, principled framework for holistic world understanding.

Findings

Current approaches are fragmented and task-specific.

A unified framework can improve robustness and generality.

Proposes a normative design specification for world models.

Abstract

World models have emerged as a critical frontier in AI research, aiming to enhance large models by infusing them with physical dynamics and world knowledge. The core objective is to enable agents to understand, predict, and interact with complex environments. However, current research landscape remains fragmented, with approaches predominantly focused on injecting world knowledge into isolated tasks, such as visual prediction, 3D estimation, or symbol grounding, rather than establishing a unified definition or framework. While these task-specific integrations yield performance gains, they often lack the systematic coherence required for holistic world understanding. In this paper, we analyze the limitations of such fragmented approaches and propose a unified design specification for world models. We suggest that a robust world model should not be a loose collection of capabilities but a normative framework that integrally incorporates interaction, perception, symbolic reasoning, and spatial representation. This work aims to provide a structured perspective to guide future research toward more general, robust, and principled models of the world.