--- title: "Baichuan-M2 — paper by Dou et al. (2025) — summary and ideas" description: "The Baichuan-M2 Team argues that reinforcement learning with verifiable rewards in medicine needs… 52 references, cited by 17 papers here." authors: ["Chengfeng Dou", "Chong Liu", "Fan Yang", "Fei Li", "Jiyuan Jia", "Mingyang Chen", "Qiang Ju", "Shuai Wang", "Shunya Dang", "Tianpeng Li", "Xiangrong Zeng", "Yijie Zhou", "Chenzheng Zhu", "Da Pan", "Fei Deng", "Guangwei Ai", "Guosheng Dong", "Hongda Zhang", "Jinyang Tai", "Jixiang Hong", "Kai Lu", "Linzhuang Sun", "Peidong Guo", "Qian Ma", "Rihui Xin", "Shihui Yang", "Shusen Zhang", "Yichuan Mo", "Zheng Liang", "Zhishou Zhang", "Hengfu Cui", "Zuyi Zhu", "Xiaochuan Wang"] year: 2025 venue: "arXiv:2509.02208" source: "https://arxiv.org/abs/2509.02208" doi: "10.48550/arxiv.2509.02208" arxiv: "2509.02208" licence: "arXiv — non-exclusive licence to distribute" licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/" summary_licence: "Elamur Cosmic License" canonical: "https://research.elamur.ai/free/en/papers/team-2025-m2-baichuan-m2-scaling-medical/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/team-2025-m2-baichuan-m2-scaling-medical/) [home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2025](https://md.research.elamur.ai/free/en/papers/2025/page/5/) / Baichuan-M2: Scaling Medical Capability with Large Verifier System # Baichuan-M2: Scaling Medical Capability with Large Verifier System **Authors:** [Chengfeng Dou](https://md.research.elamur.ai/free/en/authors/chengfeng-dou/), [Chong Liu](https://md.research.elamur.ai/free/en/authors/chong-liu/), [Fan Yang](https://md.research.elamur.ai/free/en/authors/fan-yang/), [Fei Li](https://md.research.elamur.ai/free/en/authors/fei-li/), [Jiyuan Jia](https://md.research.elamur.ai/free/en/authors/jiyuan-jia/), [Mingyang Chen](https://md.research.elamur.ai/free/en/authors/mingyang-chen/), [Qiang Ju](https://md.research.elamur.ai/free/en/authors/qiang-ju/), [Shuai Wang](https://md.research.elamur.ai/free/en/authors/shuai-wang/), Shunya Dang, [Tianpeng Li](https://md.research.elamur.ai/free/en/authors/tianpeng-li/), [Xiangrong Zeng](https://md.research.elamur.ai/free/en/authors/xiangrong-zeng/), [Yijie Zhou](https://md.research.elamur.ai/free/en/authors/yijie-zhou/), [Chenzheng Zhu](https://md.research.elamur.ai/free/en/authors/chenzheng-zhu/), [Da Pan](https://md.research.elamur.ai/free/en/authors/da-pan/), Fei Deng, Guangwei Ai, [Guosheng Dong](https://md.research.elamur.ai/free/en/authors/guosheng-dong/), Hongda Zhang, Jinyang Tai, Jixiang Hong, Kai Lu, [Linzhuang Sun](https://md.research.elamur.ai/free/en/authors/linzhuang-sun/), Peidong Guo, [Qian Ma](https://md.research.elamur.ai/free/en/authors/qian-ma/), Rihui Xin, Shihui Yang, Shusen Zhang, Yichuan Mo, [Zheng Liang](https://md.research.elamur.ai/free/en/authors/zheng-liang/), Zhishou Zhang, Hengfu Cui, Zuyi Zhu and Xiaochuan Wang · **Year:** 2025 · **Venue:** arXiv:2509.02208 · **Licence:** [arXiv — non-exclusive licence to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/) **Links:** [Publisher's page](https://arxiv.org/abs/2509.02208) · [PDF](https://arxiv.org/pdf/2509.02208) · [DOI 10.48550/arxiv.2509.02208](https://doi.org/10.48550/arxiv.2509.02208) · [arXiv 2509.02208](https://arxiv.org/abs/2509.02208) · [OpenAlex](https://openalex.org/W4416708291) **Citations:** 2 citations (OpenAlex, 2026-10-14) · [17](https://md.research.elamur.ai/free/en/papers/team-2025-m2-baichuan-m2-scaling-medical/cited-by/) in our library, of the 149,439 papers whose bibliographies we read ## Summary Medical LLMs often do well on exam-style tests such as USMLE but less well in real consultations, where information comes in gradually over many turns and communication matters. The Baichuan-M2 Team argues that reinforcement learning with verifiable rewards in medicine needs an interactive verifier, not fixed answer keys. They built two components. The first is a Patient Simulator, based on de-identified clinical records and doctor–patient dialogues, that plays patients with varied personalities and social backgrounds. The second is a Clinical Rubrics Generator, which creates scoring criteria for each case covering diagnosis, consultation logic, treatment, empathy and ethics. With this setup they trained Baichuan-M2, a 32B model, in three steps: medical mid-training, SFT with rejection sampling, and multi-stage RL using a modified GRPO. On HealthBench, Baichuan-M2 beats all open-source models and most closed ones. It scores above 32 on HealthBench Hard, which only GPT-5 had done before. The results suggest that strong clinical performance is possible at a size that can run on modest hardware. ## Key points - The simulator has three LLM-based modules: a Termination Gate, an Affective Unit and a Factual Unit. Patient personas draw on MBTI-like traits and social factors such as income and education. - Baichuan-M2 (32B) outperforms gpt-oss-120B on HealthBench and exceeds 32 on HealthBench Hard. - On a single RTX 4090 (24 GB), the W4A8-KV8 quantized model handles sequences up to 21,133 tokens and runs on SGLang without code changes. - An Eagle-3 draft model reaches 73% prediction accuracy and accepts an average of 3.28 tokens per round. This raises throughput from 41.5 to 89.9 tokens/s, a 2.17× speedup. - Stated limitations include hallucinations, unstable reasoning in edge cases, and limited tool calling and knowledge retrieval. *Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.* 📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [🩺 Medicine](https://md.research.elamur.ai/free/en/shelves/medicine/) · 275 works · [🩺 Health Informatics](https://md.research.elamur.ai/free/en/shelves/medicine/health-informatics/) · 214 works ## Cite Cite as: Chengfeng Dou, Chong Liu, Fan Yang, Fei Li, Jiyuan Jia, Mingyang Chen, Qiang Ju, Shuai Wang, Shunya Dang, Tianpeng Li, Xiangrong Zeng, Yijie Zhou, Chenzheng Zhu, Da Pan, Fei Deng, Guangwei Ai, Guosheng Dong, Hongda Zhang, Jinyang Tai, Jixiang Hong, Kai Lu, Linzhuang Sun, Peidong Guo, Qian Ma, Rihui Xin, Shihui Yang, Shusen Zhang, Yichuan Mo, Zheng Liang, Zhishou Zhang, Hengfu Cui, Zuyi Zhu and Xiaochuan Wang. 2025. Baichuan-M2: Scaling Medical Capability with Large Verifier System. arXiv:2509.02208. The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @misc{dou2025baichuan, title = {{Baichuan-M2: Scaling Medical Capability with Large Verifier System}}, author = {Chengfeng Dou, Chong Liu, Fan Yang, Fei Li, Jiyuan Jia, Mingyang Chen, Qiang Ju, Shuai Wang, Shunya Dang, Tianpeng Li, Xiangrong Zeng, Yijie Zhou, Chenzheng Zhu, Da Pan, Fei Deng, Guangwei Ai, Guosheng Dong, Hongda Zhang, Jinyang Tai, Jixiang Hong, Kai Lu, Linzhuang Sun, Peidong Guo, Qian Ma, Rihui Xin, Shihui Yang, Shusen Zhang, Yichuan Mo, Zheng Liang, Zhishou Zhang, Hengfu Cui, Zuyi Zhu and Xiaochuan Wang}, year = {2025}, doi = {10.48550/arxiv.2509.02208}, eprint = {2509.02208}, archivePrefix = {arXiv}, url = {https://doi.org/10.48550/arxiv.2509.02208} } ``` - [← previous WideSearch: Benchmarking Agentic Broad Info-Seeking](https://md.research.elamur.ai/free/en/papers/wong-2025-widesearch-benchmarking-agentic-broad-info/) - [next → Beyond Chain-of-Thought: A Survey of Chain-of-X Paradigms for LLMs](https://md.research.elamur.ai/free/en/papers/xia-2025-beyond-chain-thought-survey-chain/) - [↑ back to papers of 2025](https://md.research.elamur.ai/free/en/papers/2025/page/5/) ## References 52 references, 31 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Sagar Goyal, Eti Rastogi, Sree Prasanna Rajagopal, Dong Yuan, Fen Zhao, Jai Chintagunta, Gautam Naik, and Jeff Ward. Healai: A healthcare LLM for effective medical documentation. In Luz Angelica Caudillo-Mata, Silvio Lattanzi, Andrés Muñoz Medina, Leman Akoglu, Aristides Gionis, and Sergei Vassilvit… — [doi:10.1145/3616855.3635739](https://doi.org/10.1145/3616855.3635739) [find](https://scholar.google.com/scholar?q=Sagar+Goyal%2C+Eti+Rastogi%2C+Sree+Prasanna+Rajagopal%2C+Dong+Yuan%2C+Fen+Zhao%2C+Jai+Chintagunta%2C+Gautam+Naik%2C+and+Jeff+Ward%2E+Healai%3A+A+healthcare+LLM+for+effective+medical+documentation%2E+In+Luz+Angelica+Caudi) 2. Marco Cascella, Jonathan Montomoli, Valentina Bellini, and Elena Giovanna Bignami. Evaluating the feasibility of chatgpt in healthcare: An analysis of multiple clinical and research scenarios. J. Medical Syst., 47(1):33, 2023. doi: 10.1007/S10916-023-01925-4. URL https://doi.org/10.1007/s10916-023-0… — [doi:10.1007/s10916-023-01925-4](https://doi.org/10.1007/s10916-023-01925-4) [↗](https://doi.org/10.1007/s10916-023-0…) 3. Ziqi Yang, Xuhai Xu, Bingsheng Yao, Ethan Rogers, Shao Zhang, Stephen S. Intille, Nawar Shara, Guodong Gordon Gao, and Dakuo Wang. Talk2care: An llm-based voice assistant for communication between healthcare providers and older adults. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol., 8(2):73:1… — [doi:10.1145/3659625](https://doi.org/10.1145/3659625) [find](https://scholar.google.com/scholar?q=Ziqi+Yang%2C+Xuhai+Xu%2C+Bingsheng+Yao%2C+Ethan+Rogers%2C+Shao+Zhang%2C+Stephen+S%2E+Intille%2C+Nawar+Shara%2C+Guodong+Gordon+Gao%2C+and+Dakuo+Wang%2E+Talk2care%3A+An+llm%2Dbased+voice+assistant+for+communication+between+hea) 4. Che Liu, Haozhe Wang, Jiazhen Pan, Zhongwei Wan, Yong Dai, Fangzhen Lin, Wenjia Bai, Daniel Rueckert, and Rossella Arcucci. [Beyond distillation: Pushing the limits of medical LLM reasoning with minimalist rule-based RL](https://md.research.elamur.ai/free/en/papers/liu-2025-distillation-pushing-limits-medical-llm/). CoRR, abs/2505.17952, 2025. doi: 10.48550/ARXIV.2505.17952. URL https://doi.org/… 5. Junying Chen, Zhenyang Cai, Ke Ji, Xidong Wang, Wanlong Liu, Rongsheng Wang, Jianye Hou, and Benyou Wang. [Huatuogpt-o1, towards medical complex reasoning with llms](https://md.research.elamur.ai/free/en/papers/chen-2024-huatuogpt-o1-towards-medical-complex/). CoRR, abs/2412.18925, 2024. doi: 10.48550/ARXIV.2412.18925. URL https://doi.org/10.48550/arXiv.2412.18925. [↗](https://doi.org/10.48550/arXiv.2412.18925) 6. Daya Guo, Dejian Yang, Haowei Zhang, Junxiao Song, Ruoyu Zhang, Runxin Xu, Qihao Zhu, Shirong Ma, Peiyi Wang, Xiao Bi, et al. [Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning](https://md.research.elamur.ai/free/en/papers/deepseek-ai-2025-deepseek-r1-incentivizing-reasoning-capability/). CoRR, abs/2501.12948, 2025. doi: 10.48550/ARXIV.2501.12948. URL https://doi.org/10.48550/a… 7. Aaron Jaech, Adam Kalai, Adam Lerer, Adam Richardson, Ahmed El-Kishky, Aiden Low, Alec Helyar, Aleksander Madry, Alex Beutel, Alex Carney, et al. [Openai o1 system card](https://md.research.elamur.ai/free/en/papers/openai-2024-openai-o1-system-card/). CoRR, abs/2412.16720, 2024. doi: 10.48550/ARXIV.2412.16720. URL https://doi.org/10.48550/arXiv.2412.16720. [↗](https://doi.org/10.48550/arXiv.2412.16720) 8. Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Mingchuan Zhang, Y. K. Li, Y. Wu, and Daya Guo. [Deepseekmath: Pushing the limits of mathematical reasoning in open language models](https://md.research.elamur.ai/free/en/papers/shao-2024-deepseekmath-pushing-limits-mathematical-reasoning/). CoRR, abs/2402.03300, 2024. doi: 10.48550/ARXIV.2402.03300. URL https://doi.org/10.48550/arXiv.2402.03300. [↗](https://doi.org/10.48550/arXiv.2402.03300) 9. Anthropic. Introducing Claude 4. [https://www.anthropic.com/news/claude-4](https://www.anthropic.com/news/claude-4), May 2025. Online; accessed September 3, 2025. [↗](https://www.anthropic.com/news/claude-4) 10. Kimi Team, Yifan Bai, Yiping Bao, Guanduo Chen, Jiahao Chen, Ningxin Chen, Ruijue Chen, Yanru Chen, Yuankun Chen, Yutian Chen, et al. [Kimi K2: open agentic intelligence](https://md.research.elamur.ai/free/en/papers/kimi-team-2025-kimi-k2-open-agentic/). CoRR, abs/2507.20534, 2025. doi: 10.48550/ARXIV.2507.20534. URL https://doi.org/10.48550/arXiv.2507.20534. [↗](https://doi.org/10.48550/arXiv.2507.20534) 11. Aohan Zeng, Xin Lv, Qinkai Zheng, Zhenyu Hou, Bin Chen, Chengxing Xie, Cunxiang Wang, Da Yin, Hao Zeng, Jiajie Zhang, et al. [Glm-4.5: Agentic, reasoning, and coding (arc) foundation models](https://md.research.elamur.ai/free/en/papers/team-2025-4-glm-4-5-agentic/). arXiv preprint arXiv:2508.06471, 2025. 12. Wenyi Hong, Wenmeng Yu, Xiaotao Gu, Guo Wang, Guobing Gan, Haomiao Tang, Jiale Cheng, Ji Qi, Junhui Ji, Lihang Pan, et al. Glm-4.1v-thinking: Towards versatile multimodal reasoning with scalable reinforcement learning. CoRR, abs/2507.[01006, 2025](https://md.research.elamur.ai/free/en/papers/team-2025-v-glm-4-5v-glm/). doi: 10.48550/ARXIV.2507.01006. URL https://doi.org/1… 13. LASA Team, Weiwen Xu, Hou Pong Chan, Long Li, Mahani Aljunied, Ruifeng Yuan, Jianyu Wang, Chenghao Xiao, Guizhen Chen, Chaoqun Liu, Zhaodonghui Li, Yu Sun, Junao Shen, Chaojun Wang, Jie Tan, Deli Zhao, Tingyang Xu, Hao Zhang, and Yu Rong. Lingshu: A generalist foundation model for unified multimodal… — [doi:10.48550/arxiv.2506.07044](https://doi.org/10.48550/arxiv.2506.07044) [find](https://scholar.google.com/scholar?q=LASA+Team%2C+Weiwen+Xu%2C+Hou+Pong+Chan%2C+Long+Li%2C+Mahani+Aljunied%2C+Ruifeng+Yuan%2C+Jianyu+Wang%2C+Chenghao+Xiao%2C+Guizhen+Chen%2C+Chaoqun+Liu%2C+Zhaodonghui+Li%2C+Yu+Sun%2C+Junao+Shen%2C+Chaojun+Wang%2C+Jie+Tan%2C+Deli+Zhao) 14. National Board of Medical Examiners (NBME). Usmle scoring policies and score reporting guidelines 2024. Technical Report USMLE-POL-2024-01, Federation of State Medical Boards (FSMB) and National Board of Medical Examiners (NBME), 2024. URL [https://www.usmle.org/scoring/policies](https://www.usmle.org/scoring/policies). [↗](https://www.usmle.org/scoring/policies) 15. Rahul K. Arora, Jason Wei, Rebecca Soskin Hicks, Preston Bowman, Joaquin Quiñonero Candela, Foivos Tsimpourlas, Michael Sharman, Meghan Shah, Andrea Vallone, Alex Beutel, Johannes Heidecke, and Karan Singhal. [Healthbench: Evaluating large language models towards improved human health](https://md.research.elamur.ai/free/en/papers/arora-2025-healthbench-evaluating-large-language-models/). CoRR, abs/2505… 16. Zhaocheng Liu, Quan Tu, Wen Ye, Yu Xiao, Zhishou Zhang, Hengfu Cui, Yalun Zhu, Qiang Ju, Shizheng Li, and Jian Xie. Exploring the inquiry-diagnosis relationship with advanced patient simulators. CoRR, abs/2501.09484, 2025. doi: 10.48550/ARXIV.2501.09484. URL https://doi.org/10.48550/arXiv.2501.09484… — [doi:10.48550/arxiv.2501.09484](https://doi.org/10.48550/arxiv.2501.09484) [↗](https://doi.org/10.48550/arXiv.2501.09484…) 17. María Jesús Broch Porcar and Álvaro Castellanos-Ortega. Patient safety, what does clinical simulation and teaching innovation contribute? Medicina Intensiva (English Edition), 49(3): 165–173, 2025. [find](https://scholar.google.com/scholar?q=Mar%C3%ADa+Jes%C3%BAs+Broch+Porcar+and+%C3%81lvaro+Castellanos%2DOrtega%2E+Patient+safety%2C+what+does+clinical+simulation+and+teaching+innovation+contribute%3F+Medicina+Intensiva+%28English+Edition%29%2C+49%283%29%3A+165%E2%80%93173%2C+2025%2E) 18. Junkai Li, Siyu Wang, Meng Zhang, Weitao Li, Yunghwei Lai, Xinhui Kang, Weizhi Ma, and Yang Liu. Agent hospital: A simulacrum of hospital with evolvable medical agents. CoRR, abs/2405.02957, 2024. doi: 10.48550/ARXIV.2405.02957. URL https://doi.org/10.48550/arXiv.2405.02957. — [doi:10.48550/arxiv.2405.02957](https://doi.org/10.48550/arxiv.2405.02957) [↗](https://doi.org/10.48550/arXiv.2405.02957) 19. Wenxuan Wang, Zizhan Ma, Zheng Wang, Chenghan Wu, Jiaming Ji, Wenting Chen, Xiang Li, and Yixuan Yuan. A survey of llm-based agents in medicine: How far are we from baymax? In Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pilehvar, editors, Findings of the Association for Comput… [find](https://scholar.google.com/scholar?q=Wenxuan+Wang%2C+Zizhan+Ma%2C+Zheng+Wang%2C+Chenghan+Wu%2C+Jiaming+Ji%2C+Wenting+Chen%2C+Xiang+Li%2C+and+Yixuan+Yuan%2E+A+survey+of+llm%2Dbased+agents+in+medicine%3A+How+far+are+we+from+baymax%3F+In+Wanxiang+Che%2C+Joyce+Nabe) 20. Isabel Briggs Myers et al. The myers-briggs type indicator, volume 34. Consulting Psychologists Press Palo Alto, CA, 1962. [find](https://scholar.google.com/scholar?q=Isabel+Briggs+Myers+et+al%2E+The+myers%2Dbriggs+type+indicator%2C+volume+34%2E+Consulting+Psychologists+Press+Palo+Alto%2C+CA%2C+1962%2E) 21. Ehsan Ullah, Anil Parwani, Mirza Mansoor Baig, and Rajendra Singh. Challenges and barriers of using large language models (llm) such as chatgpt for diagnostic medicine with a focus on digital pathology –a recent scoping review. Diagnostic Pathology, 19(1):43, 2024. doi: 10.1186/s13000-024-01464-7. U… — [doi:10.1186/s13000-024-01464-7](https://doi.org/10.1186/s13000-024-01464-7) [find](https://scholar.google.com/scholar?q=Ehsan+Ullah%2C+Anil+Parwani%2C+Mirza+Mansoor+Baig%2C+and+Rajendra+Singh%2E+Challenges+and+barriers+of+using+large+language+models+%28llm%29+such+as+chatgpt+for+diagnostic+medicine+with+a+focus+on+digital+patholog) 22. Hanyu Zhang, Boyu Qiu, Yuhao Feng, Shuqi Li, Qian Ma, Xiyuan Zhang, Qiang Ju, Dong Yan, and Jian Xie. Baichuan4-finance technical report. CoRR, abs/2412.15270, 2024. doi: 10.48550/ARXIV.2412.15270. URL https://doi.org/10.48550/arXiv.2412.15270. — [doi:10.48550/arxiv.2412.15270](https://doi.org/10.48550/arxiv.2412.15270) [↗](https://doi.org/10.48550/arXiv.2412.15270) 23. Noam Wies, Yoav Levine, and Amnon Shashua. [The learnability of in-context learning](https://md.research.elamur.ai/free/en/papers/wies-2023-learnability-context-learning/). In Alice Oh, Tristan Naumann, Amir Globerson, Kate Saenko, Moritz Hardt, and Sergey Levine, editors, Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 20… 24. Zeming Wei, Yifei Wang, and Yisen Wang. [Jailbreak and guard aligned language models with only few in-context demonstrations](https://md.research.elamur.ai/free/en/papers/wei-2023-jailbreak-guard-aligned-language-models/). CoRR, abs/2310.06387, 2023. doi: 10.48550/ARXIV.2310.06387. URL https://doi.org/10.48550/arXiv.2310.06387. [↗](https://doi.org/10.48550/arXiv.2310.06387) 25. Sewon Min, Xinxi Lyu, Ari Holtzman, Mikel Artetxe, Mike Lewis, Hannaneh Hajishirzi, and Luke Zettlemoyer. [Rethinking the role of demonstrations: What makes in-context learning work?](https://md.research.elamur.ai/free/en/papers/min-2022-rethinking-role-demonstrations-what-makes/) In Yoav Goldberg, Zornitsa Kozareva, and Yue Zhang, editors, Proceedings of the 2022 Conference on Empirical Methods i… 26. Bingning Wang, Haizhou Zhao, Huozhi Zhou, Liang Song, Mingyu Xu, Wei Cheng, Xiangrong Zeng, Yupeng Zhang, Yuqi Huo, Zecheng Wang, Zhengyun Zhao, Da Pan, Fei Kou, Fei Li, Fuzhong Chen, Guosheng Dong, Han Liu, Hongda Zhang, Jin He, Jinjie Yang, Kangxi Wu, Kegeng Wu, Lei Su, Linlin Niu, Linzhuang Sun,… — [Baichuan-M1: Pushing the Medical Capability of Large Language Models](https://md.research.elamur.ai/free/en/papers/wang-2025-baichuan-m1-pushing-medical/) 27. Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Brian Ichter, Fei Xia, Ed H. Chi, Quoc V. Le, and Denny Zhou. [Chain-of-thought prompting elicits reasoning in large language models](https://md.research.elamur.ai/free/en/papers/wei-2022-chain-thought-prompting-elicits-reasoning/). In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Info… 28. Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. [Large language models are zero-shot reasoners](https://md.research.elamur.ai/free/en/papers/kojima-2022-large-language-models-zero-shot/). In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, and A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural… 29. Yuyang Wu, Yifei Wang, Tianqi Du, Stefanie Jegelka, and Yisen Wang. [When more is less: Understanding chain-of-thought length in llms](https://md.research.elamur.ai/free/en/papers/wu-2025-more-less-understanding-chain-thought/). CoRR, abs/2502.07266, 2025. doi: 10.48550/ARXIV.2502.07266. URL https://doi.org/10.48550/arXiv.2502.07266. [↗](https://doi.org/10.48550/arXiv.2502.07266) 30. Mingan Lin, Fan Yang, Yan-Bin Shen, Haoze Sun, Tianpeng Li, Tao Zhang, Chenzheng Zhu, Miao Zheng, Xu Li, Yijie Zhou, Mingyang Chen, Yanzhao Qin, Youquan Li, Hao Liang, Fei Li, Yadong Li, Mang Wang, Guosheng Dong, Kuncheng Fang, Jianhua Xu, Bin Cui, Wentao Zhang, Zenan Zhou, and Weipeng Chen. Baichua… — [Baichuan Alignment Technical Report](https://md.research.elamur.ai/free/en/papers/lin-2024-baichuan-alignment-technical-report/) 31. Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Tiantian Fan, Gaohong Liu, Lingjun Liu, Xin Liu, Haibin Lin, Zhiqi Lin, Bole Ma, Guangming Sheng, Yuxuan Tong, Chi Zhang, Mofan Zhang, Wang Zhang, Hang Zhu, Jinhua Zhu, Jiaze Chen, Jiangjie Chen, Chengyi Wang, Hongli Yu, Weinan D… — [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://md.research.elamur.ai/free/en/papers/yu-2025-dapo-open-source-llm-reinforcement/) 32. Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, and Min Lin. [Understanding r1-zero-like training: A critical perspective](https://md.research.elamur.ai/free/en/papers/liu-2025-understanding-r1-zero-like-training/). CoRR, abs/2503.20783, 2025. doi: 10.48550/ARXIV.2503.20783. URL https://doi.org/10.48550/arXiv.2503.20783. [↗](https://doi.org/10.48550/arXiv.2503.20783) 33. AIME. AIME problems and solutions, 2025. URL [https://artofproblemsolving.com/wiki/index.php/AIME_Problems_and_Solutions](https://artofproblemsolving.com/wiki/index.php/AIME_Problems_and_Solutions). [↗](https://artofproblemsolving.com/wiki/index.php/AIME_Problems_and_Solutions) 34. Xinrun Du, Yifan Yao, Kaijing Ma, Bingli Wang, Tianyu Zheng, King Zhu, Minghao Liu, Yiming Liang, Xiaolong Jin, Zhenlin Wei, et al. [Supergpqa: Scaling LLM evaluation across 285 graduate disciplines](https://md.research.elamur.ai/free/en/papers/team-2025-supergpqa-scaling-llm-evaluation-across/). CoRR, abs/2502.14739, 2025. doi: 10.48550/ARXIV.2502.14739. URL https://doi.org/10.48550/arXiv.2502.1… [↗](https://doi.org/10.48550/arXiv.2502.1…) 35. Yuxin Zuo, Shang Qu, Yifei Li, Zhang-Ren Chen, Xuekai Zhu, Ermo Hua, Kaiyan Zhang, Ning Ding, and Bowen Zhou. [MedxpertQA: Benchmarking expert-level medical reasoning and understanding](https://md.research.elamur.ai/free/en/papers/zuo-2025-medxpertqa-benchmarking-expert-level-medical/). In Forty-second International Conference on Machine Learning, 2025. URL [https://openreview.net/forum?id=IyVcxU0RKI](https://openreview.net/forum?id=IyVcxU0RKI). [↗](https://openreview.net/forum?id=IyVcxU0RKI) 36. Zenan Huang, Yihong Zhuang, Guoshan Lu, Zeyu Qin, Haokai Xu, Tianyu Zhao, Ru Peng, Jiaqi Hu, Zhanming Shen, Xiaomeng Hu, et al. Reinforcement learning with rubric anchors. arXiv preprint arXiv:2508.12790, 2025. — [arXiv:2508.12790](https://arxiv.org/abs/2508.12790) [find](https://scholar.google.com/scholar?q=Zenan+Huang%2C+Yihong+Zhuang%2C+Guoshan+Lu%2C+Zeyu+Qin%2C+Haokai+Xu%2C+Tianyu+Zhao%2C+Ru+Peng%2C+Jiaqi+Hu%2C+Zhanming+Shen%2C+Xiaomeng+Hu%2C+et+al%2E+Reinforcement+learning+with+rubric+anchors%2E+arXiv+preprint+arXiv%3A2508%2E12) 37. Zehui Ling, Deshu Chen, Hongwei Zhang, Yifeng Jiao, Xin Guo, and Yuan Cheng. Fast on the easy, deep on the hard: Efficient reasoning via powered length penalty. CoRR, abs/2506.10446, 2025. doi: 10.48550/ARXIV.2506.10446. URL https://doi.org/10.48550/arXiv.2506.10446. — [doi:10.48550/arxiv.2506.10446](https://doi.org/10.48550/arxiv.2506.10446) [↗](https://doi.org/10.48550/arXiv.2506.10446) 38. Sandhini Agarwal, Lama Ahmad, Jason Ai, Sam Altman, Andy Applebaum, Edwin Arbus, Rahul K Arora, Yu Bai, Bowen Baker, Haiming Bao, et al. [gpt-oss-120b & gpt-oss-20b model card](https://md.research.elamur.ai/free/en/papers/agarwal-2025-gpt-oss-120b-gpt-oss/). arXiv preprint arXiv:2508.10925, 2025. 39. An Yang, Anfeng Li, Baosong Yang, Beichen Zhang, Binyuan Hui, Bo Zheng, Bowen Yu, Chang Gao, Chengen Huang, Chenxu Lv, et al. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). CoRR, abs/2505.09388, 2025. doi: 10.48550/ARXIV.2505.09388. URL https://doi.org/10.48550/arXiv.2505.09388. [↗](https://doi.org/10.48550/arXiv.2505.09388) 40. Gheorghe Comanici, Eric Bieber, Mike Schaekermann, Ice Pasupat, Noveen Sachdeva, Inderjit Dhillon, Marcel Blistein, Ori Ram, Dan Zhang, Evan Rosen, et al. [Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities](https://md.research.elamur.ai/free/en/papers/comanici-2025-gemini-2-5-pushing-frontier/). CoRR, abs/2507.0… 41. Jeffrey Zhou, Tianjian Lu, Swaroop Mishra, Siddhartha Brahma, Sujoy Basu, Yi Luan, Denny Zhou, and Le Hou. [Instruction-following evaluation for large language models](https://md.research.elamur.ai/free/en/papers/zhou-2023-instruction-following-evaluation-large-language/). CoRR, abs/2311.07911, 2023. doi: 10.48550/ARXIV.2311.07911. URL https://doi.org/10.48550/arXiv.2311.07911. [↗](https://doi.org/10.48550/arXiv.2311.07911) 42. Tao Zhang, Chenglin Zhu, Yanjun Shen, Wenjing Luo, Yan Zhang, Hao Liang, Fan Yang, Mingan Lin, Yujing Qiao, Weipeng Chen, Bin Cui, Wentao Zhang, and Zenan Zhou. [Cfbench: A comprehensive constraints-following benchmark for llms](https://md.research.elamur.ai/free/en/papers/zhang-2025-cfbench-comprehensive-constraints-following-benchmark/). In Wanxiang Che, Joyce Nabende, Ekaterina Shutova, and Mohammad Taher Pi… 43. Tianle Li, Wei-Lin Chiang, Evan Frick, Lisa Dunlap, Tianhao Wu, Banghua Zhu, Joseph E. Gonzalez, and Ion Stoica. [From crowdsourced data to high-quality benchmarks: Arena-hard and benchbuilder pipeline](https://md.research.elamur.ai/free/en/papers/li-2024-crowdsourced-data-high-quality-benchmarks/). CoRR, abs/2406.11939, 2024. doi: 10.48550/ARXIV.2406.11939. URL https://doi.org/10.48550/arXiv.240… [↗](https://doi.org/10.48550/arXiv.240…) 44. Xiao Liu, Xuanyu Lei, Shengyuan Wang, Yue Huang, Andrew Feng, Bosi Wen, Jiale Cheng, Pei Ke, Yifan Xu, Weng Lam Tam, Xiaohan Zhang, Lichao Sun, Xiaotao Gu, Hongning Wang, Jing Zhang, Minlie Huang, Yuxiao Dong, and Jie Tang. [Alignbench: Benchmarking chinese alignment of large language models](https://md.research.elamur.ai/free/en/papers/liu-2023-alignbench-benchmarking-chinese-alignment/). In Lun-… 45. Yuning Wu, Jiahao Mei, Ming Yan, Chenliang Li, Shaopeng Lai, Yuran Ren, Zijia Wang, Ji Zhang, Mengyue Wu, Qin Jin, and Fei Huang. Writingbench: A comprehensive benchmark for generative writing. CoRR, abs/2503.05244, 2025. doi: 10.48550/ARXIV.2503.05244. URL https://doi.org/10.48550/arXiv.2503.05244. — [doi:10.48550/arxiv.2503.05244](https://doi.org/10.48550/arxiv.2503.05244) [↗](https://doi.org/10.48550/arXiv.2503.05244) 46. Wenhua Cheng, Weiwei Zhang, Haihao Shen, Yiyang Cai, Xin He, Kaokao Lv, and Yi Liu. Optimize weight rounding via signed gradient descent for the quantization of llms. In Yaser Al-Onaizan, Mohit Bansal, and Yun-Nung Chen, editors, Findings of the Association for Computational Linguistics: EMNLP 2024,… [find](https://scholar.google.com/scholar?q=Wenhua+Cheng%2C+Weiwei+Zhang%2C+Haihao+Shen%2C+Yiyang+Cai%2C+Xin+He%2C+Kaokao+Lv%2C+and+Yi+Liu%2E+Optimize+weight+rounding+via+signed+gradient+descent+for+the+quantization+of+llms%2E+In+Yaser+Al%2DOnaizan%2C+Mohit+Bansal) 47. Saleh Ashkboos, Amirkeivan Mohtashami, Maximilian L. Croci, Bo Li, Pashmina Cameron, Martin Jaggi, Dan Alistarh, Torsten Hoefler, and James Hensman. [Quarot: Outlier-free 4-bit inference in rotated llms](https://md.research.elamur.ai/free/en/papers/ashkboos-2024-quarot-outlier-free-4-bit/). In Amir Globersons, Lester Mackey, Danielle Belgrave, Angela Fan, Ulrich Paquet, Jakub M. Tomczak… 48. Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. GPTQ: accurate post-training quantization for generative pre-trained transformers. CoRR, abs/2210.17323, 2022. doi: 10.48550/ARXIV.2210.17323. URL https://doi.org/10.48550/arXiv.2210.17323. [↗](https://doi.org/10.48550/arXiv.2210.17323) 49. Ying Zhang, Peng Zhang, Mincong Huang, Jingyang Xiang, Yujie Wang, Chao Wang, Yineng Zhang, Lei Yu, Chuan Liu, and Wei Lin. QQQ: quality quattuor-bit quantization for large language models. CoRR, abs/2406.09904, 2024. doi: 10.48550/ARXIV.2406.09904. URL https://doi.org/10.48550/arXiv.2406.09904. — [doi:10.48550/arxiv.2406.09904](https://doi.org/10.48550/arxiv.2406.09904) [↗](https://doi.org/10.48550/arXiv.2406.09904) 50. Lianmin Zheng, Liangsheng Yin, Zhiqiang Xie, Chuyue Sun, Jeff Huang, Cody Hao Yu, Shiyi Cao, Christos Kozyrakis, Ion Stoica, Joseph E. Gonzalez, Clark W. Barrett, and Ying Sheng. [Sglang: Efficient execution of structured language model programs](https://md.research.elamur.ai/free/en/papers/zheng-2023-sglang-efficient-execution-structured-language/). In Amir Globersons, Lester Mackey, Danielle Belgrave,… 51. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph Gonzalez, Hao Zhang, and Ion Stoica. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Jason Flinn, Margo I. Seltzer, Peter Druschel, Antoine Kaufmann, and Jonathan Mace, editors… 52. Yuhui Li, Fangyun Wei, Chao Zhang, and Hongyang Zhang. Eagle-3: Scaling up inference acceleration of large language models via training-time test. arXiv preprint arXiv:2503.01840, 2025. — [arXiv:2503.01840](https://arxiv.org/abs/2503.01840) [find](https://scholar.google.com/scholar?q=Yuhui+Li%2C+Fangyun+Wei%2C+Chao+Zhang%2C+and+Hongyang+Zhang%2E+Eagle%2D3%3A+Scaling+up+inference+acceleration+of+large+language+models+via+training%2Dtime+test%2E+arXiv+preprint+arXiv%3A2503%2E01840%2C+2025%2E+%E2%80%94+%5BarXiv%3A2503%2E) *Updated 2 November 2026*