{"ID":2881583,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.11894","arxiv_id":"2508.11894","title":"QuarkMed Medical Foundation Model Technical Report","abstract":"Recent advancements in large language models have significantly accelerated their adoption in healthcare applications, including AI-powered medical consultations, diagnostic report assistance, and medical search tools. However, medical tasks often demand highly specialized knowledge, professional accuracy, and customization capabilities, necessitating a robust and reliable foundation model. QuarkMed addresses these needs by leveraging curated medical data processing, medical-content Retrieval-Augmented Generation (RAG), and a large-scale, verifiable reinforcement learning pipeline to develop a high-performance medical foundation model. The model achieved 70% accuracy on the Chinese Medical Licensing Examination, demonstrating strong generalization across diverse medical benchmarks. QuarkMed offers a powerful yet versatile personal medical AI solution, already serving over millions of users at ai.quark.cn.","short_abstract":"Recent advancements in large language models have significantly accelerated their adoption in healthcare applications, including AI-powered medical consultations, diagnostic report assistance, and medical search tools. However, medical tasks often demand highly specialized knowledge, professional accuracy, and customiz...","url_abs":"https://arxiv.org/abs/2508.11894","url_pdf":"https://arxiv.org/pdf/2508.11894v1","authors":"[\"Ao Li\",\"Bin Yan\",\"Bingfeng Cai\",\"Chenxi Li\",\"Cunzhong Zhao\",\"Fugen Yao\",\"Gaoqiang Liu\",\"Guanjun Jiang\",\"Jian Xu\",\"Liang Dong\",\"Liansheng Sun\",\"Rongshen Zhang\",\"Xiaolei Gui\",\"Xin Liu\",\"Xin Shang\",\"Yao Wu\",\"Yu Cao\",\"Zhenxin Ma\",\"Zhuang Jia\"]","published":"2025-08-16T03:47:52Z","proceeding":"cs.AI","tasks":"[\"cs.AI\"]","methods":"[\"RAG\",\"Reinforcement Learning\",\"Language Model\"]","has_code":false}