SIMMER Benchmark
Explore score history ↗SIMMER evaluates latent failures in LLM-generated plans for kitchen-domain tasks using a curated symbolic world model with 77 actions and 262 objects, scoring error-free plans and latent hazard detection.
- Released
- 2026-06-12
- Institutions
- Pennsylvania State University
- Evaluates
- General AI, Language & Knowledge, Planning, cs.CL
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
SIMMER paper
No reported scores are on record for this benchmark yet.