OpenWorldLib: A Unified Codebase and Definition of Advanced World Models

2026-04-06

AI Summary

The absence of a unified definition and standardized framework has hindered the systematic development and cross-task collaboration of world models. This work addresses this gap by formally identifying the core capabilities of advanced world models—centered on perception while integrating interaction and long-term memory—and proposes OpenWorldLib, a unified reasoning framework grounded in these principles. Designed with modularity, OpenWorldLib seamlessly incorporates perception, interaction, and memory mechanisms, enabling efficient reuse and collaborative reasoning across diverse tasks. As the first open-source infrastructure for world models, OpenWorldLib establishes a standardized platform that not only facilitates reproducible research but also charts a clear trajectory for future advancements in the field.

Abstract

World models have garnered significant attention as a promising research direction in artificial intelligence, yet a clear and unified definition remains lacking. In this paper, we introduce OpenWorldLib, a comprehensive and standardized inference framework for Advanced World Models. Drawing on the evolution of world models, we propose a clear definition: a world model is a model or framework centered on perception, equipped with interaction and long-term memory capabilities, for understanding and predicting the complex world. We further systematically categorize the essential capabilities of world models. Based on this definition, OpenWorldLib integrates models across different tasks within a unified framework, enabling efficient reuse and collaborative inference. Finally, we present additional reflections and analyses on potential future directions for world model research. Code link: https://github.com/OpenDCAI/OpenWorldLib

Problem

• world models
• unified definition
• artificial intelligence
• standardization
• framework

Innovation

• world models
• unified framework
• perception
• long-term memory
• collaborative inference