Large Language Model (LLM)-based Collective Intelligence (CI) presents a promising approach to overcoming the data wall and continuously boosting the capabilities of LLM agents. However, there is currently no dedicated arena for evolving and benchmarking LLM-based CI. To address this gap, we introduce OpenHospital, an interactive arena where physician agents can evolve CI through interactions with patient agents. This arena employs a data-in-agent-self paradigm that rapidly enhances agent capabilities and provides robust evaluation metrics for benchmarking both medical proficiency and system efficiency. Experiments demonstrate the effectiveness of OpenHospital in both fostering and quantifying CI.
@article{arxiv.2603.14771,
title = {OpenHospital: A Thing-in-itself Arena for Evolving and Benchmarking LLM-based Collective Intelligence},
author = {Peigen Liu and Rui Ding and Yuren Mao and Ziyan Jiang and Yuxiang Ye and Yunjun Gao and Ying Zhang and Renjie Sun and Longbin Lai and Zhengping Qian},
journal= {arXiv preprint arXiv:2603.14771},
year = {2026}
}