The Trinity of Consistency as a Defining Principle for General World Models

2026-02-26

AI Summary

Current general-purpose world models lack a unified theoretical framework, making it difficult to systematically evaluate their perceptual, reasoning, and physical modeling capabilities. This work proposes the “consistency triplet” as a foundational principle—encompassing modality consistency (semantic interface), spatial consistency (geometric foundation), and temporal consistency (causal engine)—thereby formally articulating the core requirements of general world models for the first time. Building on this principle, we delineate an evolutionary pathway for multimodal learning under a unified architectural perspective and introduce CoW-Bench, a new benchmark tailored for multi-frame reasoning and generation. Our study establishes a coherent theoretical and evaluation framework for general world models, exposes limitations in existing systems, and offers clear architectural guidance for developing AI systems endowed with internal world simulation capabilities.

Technology Category

• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Knowledge Representation and Reasoning: Common-Sense Reasoning
• Computer Vision: Multi-modal Vision

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

The construction of World Models capable of learning, simulating, and reasoning about objective physical laws constitutes a foundational challenge in the pursuit of Artificial General Intelligence. Recent advancements represented by video generation models like Sora have demonstrated the potential of data-driven scaling laws to approximate physical dynamics, while the emerging Unified Multimodal Model (UMM) offers a promising architectural paradigm for integrating perception, language, and reasoning. Despite these advances, the field still lacks a principled theoretical framework that defines the essential properties requisite for a General World Model. In this paper, we propose that a World Model must be grounded in the Trinity of Consistency: Modal Consistency as the semantic interface, Spatial Consistency as the geometric basis, and Temporal Consistency as the causal engine. Through this tripartite lens, we systematically review the evolution of multimodal learning, revealing a trajectory from loosely coupled specialized modules toward unified architectures that enable the synergistic emergence of internal world simulators. To complement this conceptual framework, we introduce CoW-Bench, a benchmark centered on multi-frame reasoning and generation scenarios. CoW-Bench evaluates both video generation models and UMMs under a unified evaluation protocol. Our work establishes a principled pathway toward general world models, clarifying both the limitations of current systems and the architectural requirements for future progress.

Problem

• General World Model
• Consistency
• Artificial General Intelligence
• Multimodal Learning
• Physical Reasoning

Innovation

• Trinity of Consistency
• General World Model
• Unified Multimodal Model
• CoW-Bench
• Temporal Consistency