WIP: Enhancing Game-Based Learning with AI-Driven Peer Agents

• URL: http://arxiv.org/abs/2508.01169v1
• Date: Sat, 02 Aug 2025 03:11:13 GMT
• Title: WIP: Enhancing Game-Based Learning with AI-Driven Peer Agents
• Authors: Chengzhang Zhu, Cecile H. Sam, Yanlai Wu, Ying Tang,
• Abstract summary: gamified learning platform designed to enhance engagement and knowledge retention in K-12 STEM education.<n>Initial classroom pilots utilized a multi-method assessment framework combining pre- and post-tests, in-game analytics, and qualitative feedback from students and teachers.<n>Preliminary findings indicate that significantly increases student engagement, with most participants reporting greater interest in STEM subjects.
• Score: 6.742610157385567
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This work-in-progress paper presents SPARC (Systematic Problem Solving and Algorithmic Reasoning for Children), a gamified learning platform designed to enhance engagement and knowledge retention in K-12 STEM education. Traditional approaches often struggle to motivate students or facilitate deep understanding, especially for complex scientific concepts. SPARC addresses these challenges by integrating interactive, narrative-driven gameplay with an artificial intelligence peer agent built on large language models. Rather than simply providing answers, the agent engages students in dialogue and inquiry, prompting them to explain concepts and solve problems collaboratively. The platform's design is grounded in educational theory and closely aligned with state learning standards. Initial classroom pilots utilized a multi-method assessment framework combining pre- and post-tests, in-game analytics, and qualitative feedback from students and teachers. Preliminary findings indicate that SPARC significantly increases student engagement, with most participants reporting greater interest in STEM subjects and moderate gains in conceptual understanding observed in post-test results. Ongoing development focuses on refining the AI agent, expanding curriculum integration, and improving accessibility. These early results demonstrate the potential of combining AI-driven peer support with game-based learning to create inclusive, effective, and engaging educational experiences for K-12 learners.

Related papers

• 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)
• 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)
• Innovative Tangible Interactive Games for Enhancing Artificial Intelligence Knowledge and Literacy in Elementary Education: A Pedagogical Framework [0.0]
  This paper presents an innovative framework employing tangible interactive games to enhance artificial intelligence (AI) knowledge and literacy.<n> Recognizing the growing importance of AI competencies in the 21st century, this study addresses the critical need for age-appropriate, experiential learning tools.
  arXiv  Detail & Related papers  (2025-05-31T17:40:30Z)
• A Structured Unplugged Approach for Foundational AI Literacy in Primary Education [7.495145157323768]
  We propose a structured teaching approach that fosters foundational AI literacy in primary students.<n>Our results indicate improvements in terminology understanding and usage, features description, logical reasoning, and evaluative skills.<n>The approach proved engaging, with students particularly enjoying activities that linked AI concepts to real-world reasoning.
  arXiv  Detail & Related papers  (2025-05-27T16:23:57Z)
• Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval Augmented Generation (RAG) [3.5262811753348715]
  Large language models (LLMs) facilitate dynamic pedagogical interactions but undermine confidence, trust, and instructional value.<n>Retrieval-augmented generation (RAG) grounds LLM outputs in curated knowledge but requires a clear semantic link between user input and a knowledge base.<n>We propose log-contextualized RAG (LC-RAG), which enhances RAG retrieval by using environment logs to contextualize collaborative discourse.
  arXiv  Detail & Related papers  (2025-05-22T19:31:40Z)
• LLM4CD: Leveraging Large Language Models for Open-World Knowledge Augmented Cognitive Diagnosis [56.50378080174923]
  We propose LLM4CD, which Leverages Large Language Models for Open-World Knowledge Augmented Cognitive Diagnosis.<n>Our method utilizes the open-world knowledge of LLMs to construct cognitively expressive textual representations, which are encoded to introduce rich semantic information into the CD task.<n>This approach substitutes traditional ID embeddings with semantic representations, enabling the model to accommodate new students and exercises with open-world knowledge and address the cold-start problem.
  arXiv  Detail & Related papers  (2025-05-14T14:48:00Z)
• IntelliChain: An Integrated Framework for Enhanced Socratic Method Dialogue with LLMs and Knowledge Graphs [1.810537720642316]
  This study explores how to optimize the design and collaboration of a multi-agent system tailored for Socratic teaching.<n>By incorporating knowledge graphs, this research has bolstered the capability of LLMs to handle specific educational content.
  arXiv  Detail & Related papers  (2025-01-07T03:32:29Z)
• 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)
• Towards Goal-oriented Intelligent Tutoring Systems in Online Education [69.06930979754627]
  We propose a new task, named Goal-oriented Intelligent Tutoring Systems (GITS) GITS aims to enable the student's mastery of a designated concept by strategically planning a customized sequence of exercises and assessment. We propose a novel graph-based reinforcement learning framework, named Planning-Assessment-Interaction (PAI)
  arXiv  Detail & Related papers  (2023-12-03T12:37:16Z)
• Enhancing STEM Learning with ChatGPT and Bing Chat as Objects to Think With: A Case Study [0.0]
  This study investigates the potential of ChatGPT and Bing Chat, advanced conversational AIs, as "objects-to-think-with" The study concludes that ChatGPT and Bing Chat as objects-to-think-with offer promising avenues to revolutionise STEM education.
  arXiv  Detail & Related papers  (2023-05-01T12:20:18Z)
• AGI: Artificial General Intelligence for Education [41.45039606933712]
  This position paper reviews artificial general intelligence (AGI)'s key concepts, capabilities, scope, and potential within future education. It highlights that AGI can significantly improve intelligent tutoring systems, educational assessment, and evaluation procedures. The paper emphasizes that AGI's capabilities extend to understanding human emotions and social interactions.
  arXiv  Detail & Related papers  (2023-04-24T22:31:59Z)
• Comparative Study of Learning Outcomes for Online Learning Platforms [47.5164159412965]
  Personalization and active learning are key aspects to successful learning. We run a comparative head-to-head study of learning outcomes for two popular online learning platforms.
  arXiv  Detail & Related papers  (2021-04-15T20:40:24Z)
• Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems [58.724629408229205]
  We demonstrate how traditional supervised learning and a simulator-free adversarial learning method can be used to achieve performance comparable to state-of-the-art RL-based methods. Our main goal is not to beat reinforcement learning with supervised learning, but to demonstrate the value of rethinking the role of reinforcement learning and supervised learning in optimizing task-oriented dialogue systems.
  arXiv  Detail & Related papers  (2020-09-21T12:04:18Z)
• A Dependency Syntactic Knowledge Augmented Interactive Architecture for End-to-End Aspect-based Sentiment Analysis [73.74885246830611]
  We propose a novel dependency syntactic knowledge augmented interactive architecture with multi-task learning for end-to-end ABSA. This model is capable of fully exploiting the syntactic knowledge (dependency relations and types) by leveraging a well-designed Dependency Relation Embedded Graph Convolutional Network (DreGcn) Extensive experimental results on three benchmark datasets demonstrate the effectiveness of our approach.
  arXiv  Detail & Related papers  (2020-04-04T14:59:32Z)

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.