Infants acquire language with generalization from minimal experience, whereas large language models require billions of training tokens. What underlies efficient development in humans? We investigated this problem through experiments wherein robotic agents learn to perform actions associated with imperative sentences (e.g., push red cube) via curiosity-driven self-exploration. Our approach amortizes active inference using Q-learning, enabling intrinsically motivated developmental learning. The simulations reveal key findings corresponding to observations in developmental psychology. i) Generalization improves drastically as the scale of compositional elements increases. ii) Curiosity-driven exploration enables faster learning. iii) Rote pairing of sentences and actions precedes compositional generalization. iv) Exception-handling induces U-shaped developmental performance, a pattern like representational redescription in child language learning. These results suggest that curiosity-driven active inference accounts for how intrinsically motivated sensorimotor-linguistic learning supports scalable compositional generalization and exception handling in humans and artificial agents.

翻译：婴儿仅凭极少的经验就能泛化习得语言，而大型语言模型却需要数十亿训练标记。人类高效发展的基础是什么？我们通过实验研究了这一问题：让机器人智能体在好奇心驱动的自我探索中学习执行与祈使句（如"推动红色立方体"）相关的动作。我们的方法利用Q学习摊销主动推理，实现内在动机驱动的发展性学习。模拟结果揭示了与发展心理学观察一致的关键发现：i) 随着组合元素规模的增加，泛化能力显著提升；ii) 好奇心驱动的探索能够加速学习；iii) 句子与动作的机械配对先于组合泛化；iv) 异常处理引发U型发展表现，这一模式类似于儿童语言学习中的表征重述。这些结果表明，好奇心驱动的主动推理解释了内在动机驱动的感知运动-语言学习如何支持人类与人工代理中可扩展的组合泛化及异常处理。