Benchmark
MirrorCraft Benchmark
What is MirrorCraft?
MirrorCraft is a paired benchmark for evaluating LLM-based agents under hidden rule changes in Minecraft. Each Mirror world copies a Vanilla world with…
- Released
- 2026-07-31
- Evaluates
- General AI, Language & Knowledge, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
- Reported scores
- 0
Source provenance
- Original evidence https://arxiv.org/abs/2607.29218
MirrorCraft paper
No reported scores are on record for this benchmark yet.