Lifeboat Foundation

From Stanford, Albert Einstein, & Johns Hopkins U: a multimodal agent benchmark to evaluate AI in simulated clinical environments.

From stanford, albert einstein, & johns hopkins U

AgentClinic: a multimodal agent benchmark to evaluate AI in simulated clinical environments abs: https://arxiv.org/abs/2405.07960 project page: https://agentclinic.github.io code: https://github.com/samuelschmidgall/agentclinic.

A new multimodal agent…

Agent benchmark for medical diagnosis. Contribute to SamuelSchmidgall/AgentClinic development by creating an account on GitHub.