World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Child
This work addresses the problem of enabling AI to achieve human-like reasoning and adaptation, which is foundational for advancing AI capabilities beyond incremental improvements.
The paper argues that current world models in AI lack the structured, adaptive representations seen in children's cognitive development, and proposes integrating statistical learning with six research areas—such as physics-informed learning and causal inference—to enable AI to evolve from pattern recognition to genuine reasoning.
World Models help Artificial Intelligence (AI) predict outcomes, reason about its environment, and guide decision-making. While widely used in reinforcement learning, they lack the structured, adaptive representations that even young children intuitively develop. Advancing beyond pattern recognition requires dynamic, interpretable frameworks inspired by Piaget's cognitive development theory. We highlight six key research areas -- physics-informed learning, neurosymbolic learning, continual learning, causal inference, human-in-the-loop AI, and responsible AI -- as essential for enabling true reasoning in AI. By integrating statistical learning with advances in these areas, AI can evolve from pattern recognition to genuine understanding, adaptation and reasoning capabilities.