AI Pedagogy: Dialogic Social Learning for Artificial Agents

• URL: http://arxiv.org/abs/2507.21065v2
• Date: Mon, 11 Aug 2025 18:32:56 GMT
• Title: AI Pedagogy: Dialogic Social Learning for Artificial Agents
• Authors: Sabrina Patania, Luca Annese, Cansu Koyuturk, Azzurra Ruggeri, Dimitri Ognibene,
• Abstract summary: This study explores the potential of socially mediated learning paradigms to address limitations of traditional AI training approaches.<n>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.<n>Our investigation focuses on how different pedagogical strategies impact the AI learning process in the context of acquisition.
• Score: 0.6553587309274792
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• 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

Related papers

• AI Combines, Humans Socialise: A SECI-based Experience Report on Business Simulation Games [0.0]
  This paper reports on the integration of generative AI tools into a Business Simulation Games (BSG) designed for engineering students.<n> AI was embedded as a support mechanism during the simulation to assist students in analysing events, reformulating information, and generating decision-relevant insights.<n>The results suggest a functional boundary in human-AI collaboration within simulation-based learning.
  arXiv  Detail & Related papers  (2026-02-24T07:26:16Z)
• AI Literacy for Community Colleges: Instructors' Perspectives on Scenario-Based and Interactive Approaches to Teaching AI [0.500208619516796]
  This research category full paper investigates how community college instructors evaluate interactive, no-code AI literacy resources designed for non-STEM learners.<n>As artificial intelligence becomes increasingly integrated into everyday technologies, AI literacy has emerged as a critical skill across disciplines.<n>We developed AI User, an interactive online curriculum that introduces core AI concepts through scenario - based activities set in real - world contexts.
  arXiv  Detail & Related papers  (2025-11-07T15:51:53Z)
• Beyond Automation: Socratic AI, Epistemic Agency, and the Implications of the Emergence of Orchestrated Multi-Agent Learning Architectures [0.0]
  Generative AI is no longer a peripheral tool in higher education.<n>This paper presents findings from a controlled experiment evaluating a Socratic AI Tutor.<n>Students using the Tutor reported significantly greater support for critical, independent, and reflective thinking.
  arXiv  Detail & Related papers  (2025-08-07T07:49:03Z)
• AI-Powered Math Tutoring: Platform for Personalized and Adaptive Education [0.0]
  We introduce a novel multi-agent AI tutoring platform that combines adaptive and personalized feedback, structured course generation, and textbook knowledge retrieval.<n>This system allows students to learn new topics while identifying and targeting their weaknesses, revise for exams effectively, and practice on an unlimited number of personalized exercises.
  arXiv  Detail & Related papers  (2025-07-14T20:35:16Z)
• When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration [79.69935257008467]
  We introduce Knowledge Integration and Transfer Evaluation (KITE), a conceptual and experimental framework for Human-AI knowledge transfer capabilities.<n>We conduct the first large-scale human study (N=118) explicitly designed to measure it.<n>In our two-phase setup, humans first ideate with an AI on problem-solving strategies, then independently implement solutions, isolating model explanations' influence on human understanding.
  arXiv  Detail & Related papers  (2025-06-05T20:48:16Z)
• Training a Generally Curious Agent [86.84089201249104]
  Paprika is a fine-tuning approach that enables language models to develop general decision-making capabilities.<n>Paprika teaches models to explore and adapt their behavior on a new task based on environment feedback in-context without more gradient updates.<n>Results suggest a promising path towards AI systems that can autonomously solve sequential decision-making problems.
  arXiv  Detail & Related papers  (2025-02-24T18:56:58Z)
• Towards Automated Knowledge Integration From Human-Interpretable Representations [55.2480439325792]
  We introduce and motivate theoretically the principles of informed meta-learning enabling automated and controllable inductive bias selection.<n>We empirically demonstrate the potential benefits and limitations of informed meta-learning in improving data efficiency and generalisation.
  arXiv  Detail & Related papers  (2024-02-25T15:08:37Z)
• Toward enriched Cognitive Learning with XAI [44.99833362998488]
  We introduce an intelligent system (CL-XAI) for Cognitive Learning which is supported by artificial intelligence (AI) tools. The use of CL-XAI is illustrated with a game-inspired virtual use case where learners tackle problems to enhance problem-solving skills.
  arXiv  Detail & Related papers  (2023-12-19T16:13:47Z)
• Multimodality of AI for Education: Towards Artificial General Intelligence [14.121655991753483]
  multimodal artificial intelligence (AI) approaches are paving the way towards the realization of Artificial General Intelligence (AGI) in educational contexts. This research delves deeply into the key facets of AGI, including cognitive frameworks, advanced knowledge representation, adaptive learning mechanisms, and the integration of diverse multimodal data sources. The paper also discusses the implications of multimodal AI's role in education, offering insights into future directions and challenges in AGI development.
  arXiv  Detail & Related papers  (2023-12-10T23:32:55Z)
• RLIF: Interactive Imitation Learning as Reinforcement Learning [56.997263135104504]
  We show how off-policy reinforcement learning can enable improved performance under assumptions that are similar but potentially even more practical than those of interactive imitation learning. Our proposed method uses reinforcement learning with user intervention signals themselves as rewards. This relaxes the assumption that intervening experts in interactive imitation learning should be near-optimal and enables the algorithm to learn behaviors that improve over the potential suboptimal human expert.
  arXiv  Detail & Related papers  (2023-11-21T21:05:21Z)
• Machine Psychology [54.287802134327485]
  We argue that a fruitful direction for research is engaging large language models in behavioral experiments inspired by psychology. We highlight theoretical perspectives, experimental paradigms, and computational analysis techniques that this approach brings to the table. It paves the way for a "machine psychology" for generative artificial intelligence (AI) that goes beyond performance benchmarks.
  arXiv  Detail & Related papers  (2023-03-24T13:24:41Z)
• A general framework for scientifically inspired explanations in AI [76.48625630211943]
  We instantiate the concept of structure of scientific explanation as the theoretical underpinning for a general framework in which explanations for AI systems can be implemented. This framework aims to provide the tools to build a "mental-model" of any AI system so that the interaction with the user can provide information on demand and be closer to the nature of human-made explanations.
  arXiv  Detail & Related papers  (2020-03-02T10:32:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.