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

TL;DR

GamED.AI is a hierarchical multi-agent framework that efficiently converts questions into pedagogically grounded educational games, demonstrating high validation and schema compliance with significant token reduction.

Contribution

This work introduces a novel hierarchical multi-agent system for automated educational game generation with formal validation and schema adherence, improving efficiency and quality.

Findings

Achieves 90% validation pass rate on 200 questions across five domains.

Replaces ReAct agents with 73% token reduction, saving approximately 73,500 tokens per game.

Supports generation of Bloom's-aligned games in under 60 seconds from natural language.

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.