Transform Questions into Interactive Learning Games

A hierarchical multi-agent framework that transforms instructor-provided questions into Bloom's-aligned educational games validated through formal mechanic contracts.

Games50
Domains5
Mechanics15
Levels3
Avg Latency183s

About GamED.AI

GamED.AI is 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, the system 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 and all 15 mechanics, GamED.AI achieves a 90% validation pass rate and 73% token reduction over ReAct agents (~73,500 → ~19,900 tokens/game), demonstrating that architectural discipline—not model capability—is the binding variable for alignment quality.

Each game features dual modes: Learn mode with hints and formative feedback, and Test mode with timed scoring. The demonstration interface lets users generate games from natural language, inspect Quality Gate outputs, and browse 50 curated games. Code, games, and evaluation datasets are publicly available.

Five Academic Domains

15 Game Mechanics

Two template families — Interactive Diagram (10 mechanics) and Interactive Algorithm (5 mechanics) — covering spatial reasoning, procedural execution, and higher-order Bloom's objectives.

Browse the Game Library

50 curated games spanning five domains, three education levels, and 15 interaction mechanics. All games run entirely in your browser.

Open Game Library

GamED.AI: A Hierarchical Multi-Agent Framework for Automated Educational Game Generation — ACL 2026