# Baichuan-M2: Scaling Medical Capability with Large Verifier System

arXiv: https://arxiv.org/abs/2509.02208 · HTML: https://mlsanity.com/paper/2509.02208/

## Key facts

- Cited by 59 papers in the map (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 40 of its 52 references that are in the map.
- First posted on arXiv 2 Sep 2025.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 30 of 40)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Understanding R1-Zero-Like Training: A Critical Perspective](https://mlsanity.com/paper/2503.20783/) (2025)
- [Instruction-Following Evaluation for Large Language Models](https://mlsanity.com/paper/2311.07911/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [From Crowdsourced Data to High-Quality Benchmarks: Arena-Hard and BenchBuilder Pipeline](https://mlsanity.com/paper/2406.11939/) (2024)
- [GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models](https://mlsanity.com/paper/2508.06471/) (2025)
- [GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning](https://mlsanity.com/paper/2507.01006/) (2025)
- [Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations](https://mlsanity.com/paper/2310.06387/) (2023)
- [HealthBench: Evaluating Large Language Models Towards Improved Human Health](https://mlsanity.com/paper/2505.08775/) (2025)
- [HuatuoGPT-o1, Towards Medical Complex Reasoning with LLMs](https://mlsanity.com/paper/2412.18925/) (2024)
- [Lingshu: A Generalist Foundation Model for Unified Multimodal Medical Understanding and Reasoning](https://mlsanity.com/paper/2506.07044/) (2025)
- [MedXpertQA: Benchmarking Expert-Level Medical Reasoning and Understanding](https://mlsanity.com/paper/2501.18362/) (2025)
- [Agent Hospital: A Simulacrum of Hospital with Evolvable Medical Agents](https://mlsanity.com/paper/2405.02957/) (2024)
- [When More is Less: Understanding Chain-of-Thought Length in LLMs](https://mlsanity.com/paper/2502.07266/) (2025)
- [The Learnability of In-Context Learning](https://mlsanity.com/paper/2303.07895/) (2023)
- [Reinforcement Learning with Rubric Anchors](https://mlsanity.com/paper/2508.12790/) (2025)
- [WritingBench: A Comprehensive Benchmark for Generative Writing](https://mlsanity.com/paper/2503.05244/) (2025)
- [A Survey of LLM-based Agents in Medicine: How far are we from Baymax?](https://mlsanity.com/paper/2502.11211/) (2025)

## Built on by (most cited first, 30 of 59)

- [A Survey of Reinforcement Learning for Large Reasoning Models](https://mlsanity.com/paper/2509.08827/) (2025)
- [InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training](https://mlsanity.com/paper/2510.15859/) (2025)
- [LiveMedBench: A Contamination-Free Medical Benchmark for LLMs with Automated Rubric Evaluation](https://mlsanity.com/paper/2602.10367/) (2026)
- [Baichuan-M3: Modeling Clinical Inquiry for Reliable Medical Decision-Making](https://mlsanity.com/paper/2602.06570/) (2026)
- [Fleming-R1: Toward Expert-Level Medical Reasoning via Reinforcement Learning](https://mlsanity.com/paper/2509.15279/) (2025)
- [The Dialogue That Heals: A Comprehensive Evaluation of Doctor Agents' Inquiry Capability](https://mlsanity.com/paper/2509.24958/) (2025)
- [Beyond High-Entropy Exploration: Correctness-Aware Low-Entropy Segment-Based Advantage Shaping for Reasoning LLMs](https://mlsanity.com/paper/2512.00908/) (2025)
- [From Conflict to Consensus: Boosting Medical Reasoning via Multi-Round Agentic RAG](https://mlsanity.com/paper/2603.03292/) (2026)
- [MMA-ASIA: A Multilingual and Multimodal Alignment Framework for Culturally-Grounded Evaluation](https://mlsanity.com/paper/2510.08608/) (2025)
- [MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning](https://mlsanity.com/paper/2604.08203/) (2026)
- [Scaling Large Reasoning Models beyond Human Supervision: A Path toward Superintelligence](https://mlsanity.com/paper/2608.31075/) (2026)
- [Enhancing the Medical Context-Awareness Ability of LLMs via Multifaceted Self-Refinement Learning](https://mlsanity.com/paper/2511.10067/) (2025)
- [Multidimensional Rubric-oriented Reward Model Learning via Geometric Projection Reference Constraints](https://mlsanity.com/paper/2511.16139/) (2025)
- [LingxiDiagBench: A Multi-Agent Framework for Benchmarking LLMs in Chinese Psychiatric Consultation and Diagnosis](https://mlsanity.com/paper/2602.09379/) (2026)
- [Medical Reasoning with Large Language Models: A Survey and MR-Bench](https://mlsanity.com/paper/2604.08559/) (2026)
- [Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory](https://mlsanity.com/paper/2606.09365/) (2026)
- [Generative AI for Healthcare: Fundamentals, Challenges, and Perspectives](https://mlsanity.com/paper/2510.24551/) (2025)
- [A Decade-Scale Benchmark Evaluating LLMs' Clinical Practice Guidelines Detection and Adherence in Multi-turn Conversations](https://mlsanity.com/paper/2603.25196/) (2026)
- [Patient-Zero: Scaling Synthetic Patient Agents to Real-World Distributions without Real Patient Data](https://mlsanity.com/paper/2509.11078/) (2025)
- [UMind-VL: A Generalist Ultrasound Vision-Language Model for Unified Grounded Perception and Comprehensive Interpretation](https://mlsanity.com/paper/2511.22256/) (2025)
- [Quark Medical Alignment: A Holistic Multi-Dimensional Alignment and Collaborative Optimization Paradigm](https://mlsanity.com/paper/2602.11661/) (2026)
- [Medmarks: A Comprehensive Open-Source LLM Benchmark Suite for Medical Tasks](https://mlsanity.com/paper/2605.01417/) (2026)
- [Overview of CHIP 2025 Shared Task 2: Discharge Medication Recommendation for Metabolic Diseases Based on Chinese Electronic Health Records](https://mlsanity.com/paper/2511.06230/) (2025)
- [MLB: A Scenario-Driven Benchmark for Evaluating Large Language Models in Clinical Applications](https://mlsanity.com/paper/2601.06193/) (2026)
- [LingLanMiDian: Systematic Evaluation of LLMs on TCM Knowledge and Clinical Reasoning](https://mlsanity.com/paper/2602.01779/) (2026)
- [MentalSeek-Dx: Towards Progressive Hypothetico-Deductive Reasoning for Real-world Psychiatric Diagnosis](https://mlsanity.com/paper/2602.03340/) (2026)
- [MIND: Unified Inquiry and Diagnosis RL with Criteria Grounded Clinical Supports for Psychiatric Consultation](https://mlsanity.com/paper/2603.03677/) (2026)
- [Thinking Like a Clinician: A Cognitive AI Agent for Clinical Diagnosis via Panoramic Profiling and Adversarial Debate](https://mlsanity.com/paper/2604.23605/) (2026)
- [MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports](https://mlsanity.com/paper/2605.03103/) (2026)
- [Baichuan-M4: A Clinical-Grade Medical Agent System for Continuous Care](https://mlsanity.com/paper/2606.08982/) (2026)

## Abstract (arXiv)

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.