让AI像孩子一样理解世界，从识别模式到真正推理。
World Models in Artificial Intelligence: Sensing, Learning, and Reasoning Like a Child
- 结合皮亚杰认知发展理论，构建动态可解释的智能框架。
- 提出六项关键研究方向，推动AI从感知到理解跃迁。
- 适合关注通用人工智能与可解释AI的研究者。
世界模型使人工智能能够预测结果、理解环境并指导决策。尽管在强化学习中广泛应用，现有模型仍缺乏儿童般的结构化、自适应表征能力。突破模式识别需借鉴皮亚杰认知发展理论，发展动态、可解释的框架。本文强调六个核心研究方向：物理信息学习、神经符号学习、持续学习、因果推断、人机协同AI与负责任AI，是实现真正推理的关键。通过将统计学习与这些领域进展融合，AI有望从模式识别迈向真正的理解、适应与推理能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。