Curiosity-powered AI robots learn language faster and behave like children

The OIST team has developed a curiosity-driven AI system that enables virtual robots to learn language more like children. (Representational image)Yuichiro Chino A team of researchers has developed AI-powered virtual robots that learn to understand language more efficiently by rewarding curiosity rather than rote instruction, offering new insights into how children acquire language. Researchers at the Okinawa Institute of Science and Technology (OIST) found that robots trained to explore and satisfy their curiosity mastered language-based tasks in about half the time of conventionally trained robots. The brain-inspired system also displayed spontaneous play-like behavior and improved ability to handle unfamiliar situations, suggesting that curiosity-driven learning could make future AI systems more adaptable and human-like. “We were amazed by the play-like behavior and exception-handling performance that emerged independently during training,” says Theodore Tinker, study first author and PhD student in the Cognitive Neurorobotics Research Unit at OIST, in a statement. Curious AI learns The OIST team has developed a curiosity-driven AI system that enables virtual robots to learn language more like children, offering new insights into both artificial intelligence and human language acquisition. Unlike large language models (LLMs), which generate responses by predicting the most likely next word from vast datasets, the researchers used a brain-inspired architecture known as a Predictive Coding-inspired Variational Recurrent Neural Network (PV-RNN). The model is designed to minimize “Free Energy” by balancing two competing goals: improving prediction accuracy while minimizing changes to its internal beliefs. In other words, the robot aims to correctly understand the world while maintaining a stable internal model of it. To encourage exploration, the team combined the PV-RNN with reinforcement learning. Robots received an external reward for completing language-guided tasks and an internal reward for satisfying curiosity by exploring unfamiliar situations that required updating their internal understanding. This balance between stability and exploration enabled the robots to discover new solutions to complex tasks more efficiently. During training, the curious robots displayed unexpected play-like behavior. Even after mastering assigned tasks, they continued experimenting by knocking over objects, despite receiving no direct instruction to do so. Researchers found that this spontaneous exploration accelerated language learning, suggesting that curiosity-driven play may be crucial to acquiring knowledge, much as it is for young children. “The robots are not thinking like children, and their situation is very abstract compared to the extremely dense language environments of children. But this abstract environment allows us to study the impact of curiosity within a very convincing model of how humans learn to process language,” said Jun Tani, study senior author and head of the OIST unit, in a statement. Robots learn exceptions The study also sheds light on a long-standing question in linguistics known as Noam Chomsky’s “Poverty of the Stimulus” problem, which asks how children rapidly learn language despite receiving incomplete and imperfect input. The researchers found that curiosity alone was not enough; it had to be paired with a rich and diverse language environment. Robots exposed to only 48 language combinations achieved about 25 percent generalization. In comparison, those trained with 180 combinations reached around 85 percent, demonstrating that varied linguistic exposure dramatically improved their ability to understand previously unseen instructions. Another surprising finding was that the robots exhibited a learning pattern similar to toddlers’ U-shaped learning curve. To test this, researchers deliberately reversed the meanings of two language tasks. Initially, the robots learned the exceptions correctly, but as they generalized broader language rules, their performance temporarily declined before recovering as they mastered the exceptions. This mirrors how children often say “goed” or “runned” before eventually learning irregular verbs correctly. According to the researchers, the emergence of this behavior was entirely unexpected, as the AI model contained no explicit mechanism for handling exceptions or overgeneralization. Beyond improving robotic language learning, the transparent design of the PV-RNN allows scientists to observe the AI’s internal decision-making process in real time. Unlike massive black-box AI systems, researchers can directly examine how the robot updates its beliefs, making the model a valuable platform for studying both human cognition and the mechanisms underlying language acquisition. Recommended ArticlesGet the latest in engineering, tech, space & science - delivered daily to your inbox.Jijo is an automotive and business journalist based in India. Armed with a BA in History (Honors) from St. Stephen's College, Delhi University, and a PG diploma in Journalism from the Indian Institute of Mass Communication, Delhi, he has worked for news agencies, national newspapers, and automotive magazines. In his spare time, he likes to go off-roading, engage in political discourse, travel, and teach languages.