_version_ 1866918134272753664
author M2 Team
Dou, Chengfeng
Liu, Chong
Yang, Fan
Li, Fei
Jia, Jiyuan
Chen, Mingyang
Ju, Qiang
Wang, Shuai
Dang, Shunya
Li, Tianpeng
Zeng, Xiangrong
Zhou, Yijie
Zhu, Chenzheng
Pan, Da
Deng, Fei
Ai, Guangwei
Dong, Guosheng
Zhang, Hongda
Tai, Jinyang
Hong, Jixiang
Lu, Kai
Sun, Linzhuang
Guo, Peidong
Ma, Qian
Xin, Rihui
Yang, Shihui
Zhang, Shusen
Mo, Yichuan
Liang, Zheng
Zhang, Zhishou
Cui, Hengfu
Zhu, Zuyi
Wang, Xiaochuan
author_facet M2 Team
Dou, Chengfeng
Liu, Chong
Yang, Fan
Li, Fei
Jia, Jiyuan
Chen, Mingyang
Ju, Qiang
Wang, Shuai
Dang, Shunya
Li, Tianpeng
Zeng, Xiangrong
Zhou, Yijie
Zhu, Chenzheng
Pan, Da
Deng, Fei
Ai, Guangwei
Dong, Guosheng
Zhang, Hongda
Tai, Jinyang
Hong, Jixiang
Lu, Kai
Sun, Linzhuang
Guo, Peidong
Ma, Qian
Xin, Rihui
Yang, Shihui
Zhang, Shusen
Mo, Yichuan
Liang, Zheng
Zhang, Zhishou
Cui, Hengfu
Zhu, Zuyi
Wang, Xiaochuan
contents As large language models (LLMs) advance in conversational and reasoning capabilities, their practical application in healthcare has become a critical research focus. However, there is a notable gap between the performance of medical LLMs on static benchmarks such as USMLE and their utility in real-world clinical decision-making. This discrepancy arises because traditional exams fail to capture the dynamic, interactive nature of medical consultations. To address this challenge, we introduce a novel dynamic verification framework that moves beyond static answer verifier, establishing a large-scale, high-fidelity interactive reinforcement learning system. Our framework comprises two key components: a Patient Simulator that creates realistic clinical environments using de-identified medical records, and a Clinical Rubrics Generator that dynamically produces multi-dimensional evaluation metrics. Building on this foundation, we develop Baichuan-M2, a 32B-parameter medical augmented reasoning model trained through a multi-stage reinforcement learning strategy with an improved Group Relative Policy Optimization (GRPO) algorithm. Evaluated on HealthBench, Baichuan-M2 outperforms all other open-source models and most advanced closed-source counterparts, achieving a score above 32 on the challenging HealthBench Hard benchmark-previously exceeded only by GPT-5. Our work demonstrates that robust dynamic verifier system is essential for aligning LLM capabilities with practical clinical applications, establishing a new Pareto front in the performance-parameter trade-off for medical AI deployment.
format Preprint
id arxiv_https___arxiv_org_abs_2509_02208
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Baichuan-M2: Scaling Medical Capability with Large Verifier System
M2 Team
Dou, Chengfeng
Liu, Chong
Yang, Fan
Li, Fei
Jia, Jiyuan
Chen, Mingyang
Ju, Qiang
Wang, Shuai
Dang, Shunya
Li, Tianpeng
Zeng, Xiangrong
Zhou, Yijie
Zhu, Chenzheng
Pan, Da
Deng, Fei
Ai, Guangwei
Dong, Guosheng
Zhang, Hongda
Tai, Jinyang
Hong, Jixiang
Lu, Kai
Sun, Linzhuang
Guo, Peidong
Ma, Qian
Xin, Rihui
Yang, Shihui
Zhang, Shusen
Mo, Yichuan
Liang, Zheng
Zhang, Zhishou
Cui, Hengfu
Zhu, Zuyi
Wang, Xiaochuan
Machine Learning
Artificial Intelligence
As large language models (LLMs) advance in conversational and reasoning capabilities, their practical application in healthcare has become a critical research focus. However, there is a notable gap between the performance of medical LLMs on static benchmarks such as USMLE and their utility in real-world clinical decision-making. This discrepancy arises because traditional exams fail to capture the dynamic, interactive nature of medical consultations. To address this challenge, we introduce a novel dynamic verification framework that moves beyond static answer verifier, establishing a large-scale, high-fidelity interactive reinforcement learning system. Our framework comprises two key components: a Patient Simulator that creates realistic clinical environments using de-identified medical records, and a Clinical Rubrics Generator that dynamically produces multi-dimensional evaluation metrics. Building on this foundation, we develop Baichuan-M2, a 32B-parameter medical augmented reasoning model trained through a multi-stage reinforcement learning strategy with an improved Group Relative Policy Optimization (GRPO) algorithm. Evaluated on HealthBench, Baichuan-M2 outperforms all other open-source models and most advanced closed-source counterparts, achieving a score above 32 on the challenging HealthBench Hard benchmark-previously exceeded only by GPT-5. Our work demonstrates that robust dynamic verifier system is essential for aligning LLM capabilities with practical clinical applications, establishing a new Pareto front in the performance-parameter trade-off for medical AI deployment.
title Baichuan-M2: Scaling Medical Capability with Large Verifier System
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.02208