Jul 2026
MirrorCraft: Paired Evaluation under Hidden Rule Changes in Minecraft
MirrorCraft is introduced, a paired benchmark for evaluating agents under hidden rule changes in Minecraft and provides a controlled setting for studying how agents use gameplay outcomes when the rules of the current world differ from familiar ones.
Jian-Xi Gao, Beini Hu, Run-Ze Li et al.
· arXiv.org · 0 citations