Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care
2026-06-08 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors developed Baichuan-M4, a medical AI system designed to support ongoing patient care rather than just answering one medical question at a time. It combines a special runtime environment, a core reasoning model trained with advanced reinforcement learning techniques, and a set of clinical tools that handle patient records, evidence retrieval, and medical images. Their model performs well in tests covering medical knowledge, patient consultations, memory of past interactions, and understanding medical images, while keeping errors low. This approach aims to make AI more helpful and reliable in real-world healthcare settings.
medical large modelreinforcement learningpatient memorymulti-agent systemevidence-based retrievalmultimodal medical perceptionOSCE-style consultationhallucination ratepolicy optimizationcurriculum learning
Authors
Aiyuan Yang, Chengfeng Dou, Da Pan, Dian Wang, Fan Yang, Fei Deng, Fei Li, Guangwei Ai, Hui Liu, Hongda Zhang, Jinyang Tai, Kai Lu, Lijun Liu, Linwei Chen, Linyu Li, Meiqing Guo, Peidong Guo, Qiang Ju, Rihui Xin, Shuai Wang, XinKai Ma, Xudong Chen, Yichuan Mo, Canbin Piao, Leyi Pan, Yihe Luo, Zian Wang
Abstract
Baichuan-M4 is Baichuan Intelligence's clinical-grade medical large model, designed for \emph{continuous care} rather than single-turn medical question answering. It is built as a coordinated medical agent system around three pillars: \textbf{Baichuan-Harness}, a unified runtime that keeps reinforcement-learning training and real-world deployment consistent while enforcing action constraints, tool use, long-term patient memory, and multi-agent coordination; a \textbf{core reasoning model} trained with a continuous-care reinforcement-learning framework that integrates span-level reward modeling (SPAR++), reasoning-path compression, curriculum learning, and stabilized policy optimization; and a \textbf{clinical tool layer} for patient-memory management, authoritative evidence-based retrieval, and multimodal medical perception across documents, X-rays, and dermatology. On a cross-dimensional medical evaluation suite, Baichuan-M4 attains leading results in static medical knowledge and safety, dynamic OSCE-style consultation, long-context clinical memory, evidence-based retrieval, medical document OCR, and multimodal image understanding, while lowering the hallucination rate to 3.3\%.