Dialogic Social Learning for Artificial Agents: Enhancing LLM Ontology Acquisition through Mixed-Initiative Educational Interactions

2025-05-25

AI Summary

Large language models (LLMs) excel at offline data processing but struggle to efficiently acquire and integrate dynamic online knowledge; conventional supervised or reinforcement learning paradigms are constrained by static datasets and sparse feedback. Method: We propose the “AI Social Gymnasium” framework—a bidirectional pedagogical dialogue system between AI teachers and learners—guided by Vygotskian sociocultural theory. It integrates multi-agent systems, structured prompting, and a dynamic ontology learning architecture to enable hybrid active interaction, combining top-down instruction with learner-initiated questioning. Contribution/Results: Experiments demonstrate significant improvements in LLMs’ ontology acquisition, application accuracy, and response quality over unidirectional teaching and direct retrieval of structured knowledge baselines. This work is the first to systematically embed socially grounded collaborative learning into LLM training paradigms.

Technology Category

• Multiagent Systems: Multiagent Learning
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Large Language Models (LLMs) have demonstrated remarkable capabilities in processing extensive offline datasets. However, they often face challenges in acquiring and integrating complex, knowledge online. Traditional AI training paradigms, predominantly based on supervised learning or reinforcement learning, mirror a'Piagetian'model of independent exploration. These approaches typically rely on large datasets and sparse feedback signals, limiting the models'ability to learn efficiently from interactions. Drawing inspiration from Vygotsky's sociocultural theory, this study explores the potential of socially mediated learning paradigms to address these limitations. We introduce a dynamic environment, termed the'AI Social Gym', where an AI learner agent engages in dyadic pedagogical dialogues with knowledgeable AI teacher agents. These interactions emphasize external, structured dialogue as a core mechanism for knowledge acquisition, contrasting with methods that depend solely on internal inference or pattern recognition. Our investigation focuses on how different pedagogical strategies impact the AI learning process in the context of ontology acquisition. Empirical results indicate that such dialogic approaches-particularly those involving mixed-direction interactions combining top-down explanations with learner-initiated questioning-significantly enhance the LLM's ability to acquire and apply new knowledge, outperforming both unidirectional instructional methods and direct access to structured knowledge, formats typically present in training datasets. These findings suggest that integrating pedagogical and psychological insights into AI and robot training can substantially improve post-training knowledge acquisition and response quality. This approach offers a complementary pathway to existing strategies like prompt engineering

Problem

• Enhancing online knowledge acquisition in large language models
• Addressing limitations of traditional AI training paradigms
• Improving knowledge integration through dialogic social learning

Innovation

• Dialogic social learning with AI teacher agents
• Mixed-direction pedagogical interactions for knowledge acquisition
• AI Social Gym environment for structured dialogue learning