HealthCraft is the first public RL safety environment for emergency medicine that evaluates frontier LLMs on trajectory-level safety with a dual-layer rubric, showing low multi-step performance and high safety failure rates.
arXiv preprint arXiv:2602.16179v5 , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
HealthCraft: A Reinforcement Learning Safety Environment for Emergency Medicine
HealthCraft is the first public RL safety environment for emergency medicine that evaluates frontier LLMs on trajectory-level safety with a dual-layer rubric, showing low multi-step performance and high safety failure rates.