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.
More from Research
- ICLR 2027 desk-rejects papers after reviewers fail to file AI-use disclosure forms — algo_diver · 2026-11-20
- Chorus paper: shared n-gram tables cut memory 87% while beating DeepSeek's Engram — brown2green · 2026-11-20
- Synthetic benchmarks for concept bottleneck models isolate failure modes, NeurIPS 2026 — berkustun · 2026-11-20
- Inhabitant: training-free LLM agent completes 74/75 long-horizon household tasks — Yao Zhang · 2026-11-20
- EPFL team unveils unified 3D generative model for structure-based drug design and docking — HannesStaerk · 2026-11-20
- ICLR 2027 Review Score Distribution: 40,160 Submissions, a 3.0 Average Only Ranks Top 14% — May_F1_ · 2026-11-20