OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective Intelligence
Researchers have developed OpenHospital, a novel interactive arena designed to evolve and benchmark collective intelligence in Large Language Model (LLM) agents. This platform facilitates the development of CI by enabling physician agents to interact with patient agents, employing a data-in-agent-self paradigm. The system aims to enhance agent capabilities and provide robust evaluation metrics for medical proficiency and system efficiency, demonstrating its effectiveness in fostering and quantifying CI. AI
IMPACT Provides a dedicated platform for evaluating and advancing LLM agent collective intelligence in a simulated medical environment.