将教师提问自动转为可玩的教育游戏，支持15种交互机制。
GamED.AI: A Hierarchical Multi-Agent Framework for Automated Educational Game Generation
- 分阶段多智能体架构，通过结构化规则确保生成质量。
- 200个问题测试中90%通过验证，生成效率提升73%。
- 适合教育技术开发者快速构建符合认知目标的游戏。
我们提出GamEDAI，一种分层多智能体框架，能将教师提供的问题转化为可玩且具备教学依据的教育游戏，并通过形式化机制合约进行验证。系统基于分阶段的LangGraph子图、确定性质量门控和结构化Pydantic模式，支持两类模板共15种交互机制，覆盖空间推理、过程执行及高阶布卢姆认知目标。在五个学科领域的200个问题上评估，系统达到90%验证通过率、98.3%模式合规率，相比ReAct代理实现73%的令牌减少（约73,500→约19,900令牌/游戏），单次生成成本仅0.46美元。结果表明，阶段限定的架构结构对对齐质量的影响强于提示策略本身。演示环节可在60秒内从自然语言生成布卢姆目标对齐的游戏，逐阶段查看质量门控输出，并浏览涵盖全部15种机制的50款精选游戏。
原文摘要 · Abstract (English)
We introduce GamEDAI, a hierarchical multi-agent framework that transforms instructor-provided questions into fully playable, pedagogically grounded educational games validated through formal mechanic contracts. Built on phase-based LangGraph sub-graphs, deterministic Quality Gates, and structured Pydantic schemas, GamEDAI supports two template families encompassing 15 interaction mechanics across spatial reasoning, procedural execution, and higher-order Bloom's Taxonomy objectives. Evaluated on 200 questions spanning five subject domains, the system achieves a 90% validation pass rate, 98.3% schema compliance, and 73% token reduction over ReAct agents (${\sim}$73,500 $\rightarrow$ ${\sim}$19,900 tokens/game) at $0.46 per game. Within this model configuration, these results suggest that phase-bounded architectural structure correlates more strongly with alignment quality than prompting strategy alone. Our demonstration lets attendees generate Bloom's-aligned games from natural language in under 60 seconds, inspect Quality Gate outputs at each pipeline phase, and browse a curated library of 50 games spanning all 15 mechanic types.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。