PlayCraft: AI agents play-test games and revise them to boost engagement

Weihao Cheng · hf · 2026-11-20

The PlayCraft paper proposes an automated game-design framework that iterates on games from agent play experience: a vision-based player agent plays across episodes with memory and reports progress, decisions and reflections; a crafter agent estimates player abilities, predicts performance against a target learning progression, and revises the game to close gaps. Measured by learning gain and learning slope, revised games beat the initial versions across three intelligence settings.

Original post →

More from Research

Research channel →