GAMED.AI: A Hierarchical Multi-Agent Framework for Automated Educational Game Generation

2026-04-26

AI Summary

This study addresses the challenge of automatically transforming teacher-provided natural language prompts into educationally aligned, engaging, and validated educational games. The authors propose a hierarchical multi-agent framework that integrates formal mechanism contracts with staged quality gates, leveraging LangGraph subgraphs, structured Pydantic schemas, deterministic Quality Gates, and Bloom’s taxonomy alignment to support 15 distinct interaction types. Evaluated on 200 cross-disciplinary prompts, the approach achieves a 90% validation pass rate and 98.3% schema compliance, with an average generation cost of just $0.46 per game. Token consumption is reduced by 73% (averaging 19,900 tokens per game), substantially enhancing both generation efficiency and pedagogical fidelity.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Multiagent Systems: Mechanism Design
• Natural Language Processing: Prompt Engineering / Prompting

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• 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

Abstract

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.

Problem

• educational game generation
• multi-agent framework
• pedagogical alignment
• game mechanics
• automated validation

Innovation

• hierarchical multi-agent framework
• educational game generation
• mechanic contracts
• Quality Gates
• LangGraph