{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:07Z","timestamp":1786120807348,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3819019","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"11073-11084","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["<scp>MedJudge:<\/scp>\n                    Medical Multimodal Reward Modeling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-1926-8478","authenticated-orcid":false,"given":"Yunhong","family":"He","sequence":"first","affiliation":[{"name":"Independent Researcher, Chicago, IL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6322-6096","authenticated-orcid":false,"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[{"name":"Lehigh University, Bethlehem, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-3232-1023","authenticated-orcid":false,"given":"Jiarong","family":"Qian","sequence":"additional","affiliation":[{"name":"Rice University, Houston, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4870-8492","authenticated-orcid":false,"given":"Zhengqing","family":"Yuan","sequence":"additional","affiliation":[{"name":"University of Notre Dame, southbend, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-6002-125X","authenticated-orcid":false,"given":"Yanfang","family":"Ye","sequence":"additional","affiliation":[{"name":"University of Notre Dame, southbend, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6133-6988","authenticated-orcid":false,"given":"Jing","family":"Huang","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1539-7939","authenticated-orcid":false,"given":"Lichao","family":"Sun","sequence":"additional","affiliation":[{"name":"Lehigh University, Bethlehem, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Preston Bowman, Joaquin Qui\u00f1onero-Candela, Foivos Tsimpourlas, Michael Sharman, Meghan Shah, Andrea Vallone, Alex Beutel, et al.","author":"Arora Rahul K","year":"2025","unstructured":"Rahul K Arora, Jason Wei, Rebecca Soskin Hicks, Preston Bowman, Joaquin Qui\u00f1onero-Candela, Foivos Tsimpourlas, Michael Sharman, Meghan Shah, Andrea Vallone, Alex Beutel, et al. 2025. Healthbench: Evaluating large language models towards improved human health. arXiv preprint arXiv:2505.08775 (2025)."},{"key":"e_1_3_2_1_2_1","unstructured":"Shuai Bai Yuxuan Cai Ruizhe Chen Keqin Chen Xionghui Chen Zesen Cheng Lianghao Deng Wei Ding Chang Gao Chunjiang Ge Wenbin Ge Zhifang Guo Qidong Huang Jie Huang Fei Huang Binyuan Hui Shutong Jiang Zhaohai Li Mingsheng Li Mei Li Kaixin Li Zicheng Lin Junyang Lin Xuejing Liu Jiawei Liu Chenglong Liu Yang Liu Dayiheng Liu Shixuan Liu Dunjie Lu Ruilin Luo Chenxu Lv Rui Men Lingchen Meng Xuancheng Ren Xingzhang Ren Sibo Song Yuchong Sun Jun Tang Jianhong Tu Jianqiang Wan Peng Wang Pengfei Wang Qiuyue Wang Yuxuan Wang Tianbao Xie Yiheng Xu Haiyang Xu Jin Xu Zhibo Yang Mingkun Yang Jianxin Yang An Yang Bowen Yu Fei Zhang Hang Zhang Xi Zhang Bo Zheng Humen Zhong Jingren Zhou Fan Zhou Jing Zhou Yuanzhi Zhu and Ke Zhu. 2025. Qwen3-VL Technical Report. arXiv:2511.21631 [cs.CV] https:\/\/arxiv.org\/abs\/2511.21631"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.2307\/2334029"},{"key":"e_1_3_2_1_4_1","volume-title":"Deep reinforcement learning from human preferences. Advances in neural information processing systems 30","author":"Christiano Paul F","year":"2017","unstructured":"Paul F Christiano, Jan Leike, Tom Brown, Miljan Martic, Shane Legg, and Dario Amodei. 2017. Deep reinforcement learning from human preferences. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_5_1","unstructured":"Tri Dao. 2023. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. arXiv:2307.08691 [cs.LG] https:\/\/arxiv.org\/abs\/2307.08691"},{"key":"e_1_3_2_1_6_1","volume-title":"Med-RewardBench: Benchmarking Reward Models and Judges for Medical Multimodal Large Language Models. arXiv preprint arXiv:2508.21430","author":"Ding Meidan","year":"2025","unstructured":"Meidan Ding, Jipeng Zhang,WenxuanWang, Cheng-Yi Li,Wei-Chieh Fang, Hsin-Yu Wu, Haiqin Zhong, Wenting Chen, and Linlin Shen. 2025. Med-RewardBench: Benchmarking Reward Models and Judges for Medical Multimodal Large Language Models. arXiv preprint arXiv:2508.21430 (2025)."},{"key":"e_1_3_2_1_7_1","unstructured":"Chengfeng Dou Chong Liu Fan Yang Fei Li Jiyuan Jia Mingyang Chen Qiang Ju Shuai Wang Shunya Dang Tianpeng Li et al. 2025. Baichuan-m2: Scaling medical capability with large verifier system. arXiv preprint arXiv:2509.02208 (2025)."},{"key":"e_1_3_2_1_8_1","volume-title":"Medthink: Explaining medical visual question answering via multimodal decision-making rationale. arXiv preprint arXiv:2404.12372","author":"Gai Xiaotang","year":"2024","unstructured":"Xiaotang Gai, Chenyi Zhou, Jiaxiang Liu, Yang Feng, Jian Wu, and Zuozhu Liu. 2024. Medthink: Explaining medical visual question answering via multimodal decision-making rationale. arXiv preprint arXiv:2404.12372 (2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"},{"key":"e_1_3_2_1_10_1","volume-title":"Reward reasoning model. arXiv preprint arXiv:2505.14674","author":"Guo Jiaxin","year":"2025","unstructured":"Jiaxin Guo, Zewen Chi, Li Dong, Qingxiu Dong, Xun Wu, Shaohan Huang, and FuruWei. 2025. Reward reasoning model. arXiv preprint arXiv:2505.14674 (2025)."},{"key":"e_1_3_2_1_11_1","volume-title":"Pathvqa: 30000 questions for medical visual question answering. arXiv preprint arXiv:2003.10286","author":"He Xuehai","year":"2020","unstructured":"Xuehai He, Yichen Zhang, Luntian Mou, Eric Xing, and Pengtao Xie. 2020. Pathvqa: 30000 questions for medical visual question answering. arXiv preprint arXiv:2003.10286 (2020)."},{"key":"e_1_3_2_1_12_1","unstructured":"Aaron Jaech Adam Kalai Adam Lerer Adam Richardson Ahmed El-Kishky Aiden Low Alec Helyar Aleksander Madry Alex Beutel Alex Carney et al. 2024. Openai o1 system card. arXiv preprint arXiv:2412.16720 (2024)."},{"key":"e_1_3_2_1_13_1","volume-title":"Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, et al.","author":"Lambert Nathan","year":"2025","unstructured":"Nathan Lambert, Valentina Pyatkin, Jacob Morrison, Lester James Validad Miranda, Bill Yuchen Lin, Khyathi Chandu, Nouha Dziri, Sachin Kumar, Tom Zick, Yejin Choi, et al. 2025. Rewardbench: Evaluating reward models for language modeling. In Findings of the Association for Computational Linguistics: NAACL 2025. 1755-1797."},{"key":"e_1_3_2_1_14_1","volume-title":"Asma Ben Abacha, and Dina Demner-Fushman","author":"Lau Jason J","year":"2018","unstructured":"Jason J Lau, Soumya Gayen, Asma Ben Abacha, and Dina Demner-Fushman. 2018. A dataset of clinically generated visual questions and answers about radiology images. Scientific data 5, 1 (2018), 1-10."},{"key":"e_1_3_2_1_15_1","volume-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890","author":"Li Chunyuan","year":"2023","unstructured":"Chunyuan Li, Cliff Wong, Sheng Zhang, Naoto Usuyama, Haotian Liu, Jianwei Yang, Tristan Naumann, Hoifung Poon, and Jianfeng Gao. 2023. Llava-med: Training a large language-and-vision assistant for biomedicine in one day. arXiv preprint arXiv:2306.00890 (2023)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI48211.2021.9434010"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.1698"},{"key":"e_1_3_2_1_18_1","volume-title":"Inference-time scaling for generalist reward modeling. arXiv preprint arXiv:2504.02495","author":"Liu Zijun","year":"2025","unstructured":"Zijun Liu, Peiyi Wang, Runxin Xu, Shirong Ma, Chong Ruan, Peng Li, Yang Liu, and Yu Wu. 2025. Inference-time scaling for generalist reward modeling. arXiv preprint arXiv:2504.02495 (2025)."},{"key":"e_1_3_2_1_19_1","volume-title":"Michael Moseley, Curtis Langlotz, Akshay S Chaudhari, et al.","author":"Ostmeier Sophie","year":"2024","unstructured":"Sophie Ostmeier, Justin Xu, Zhihong Chen, Maya Varma, Louis Blankemeier, Christian Bluethgen, Arne Edward Michalson Md, Michael Moseley, Curtis Langlotz, Akshay S Chaudhari, et al. 2024. Green: Generative radiology report evaluation and error notation. In Findings of the association for computational linguistics: EMNLP 2024. 374-390."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Long Ouyang Jeffrey Wu Xu Jiang Diogo Almeida Carroll Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray et al. 2022. Training language models to follow instructions with human feedback. Advances in neural information processing systems 35 (2022) 27730-27744.","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2025.104946"},{"key":"e_1_3_2_1_22_1","unstructured":"Andrew Sellergren Sahar Kazemzadeh Tiam Jaroensri Atilla Kiraly Madeleine Traverse Timo Kohlberger Shawn Xu Fayaz Jamil C\u00edan Hughes Charles Lau Justin Chen Fereshteh Mahvar Liron Yatziv Tiffany Chen Bram Sterling Stefanie Anna Baby Susanna Maria Baby Jeremy Lai Samuel Schmidgall Lu Yang Kejia Chen Per Bjornsson Shashir Reddy Ryan Brush Kenneth Philbrick Mercy Asiedu Ines Mezerreg Howard Hu Howard Yang Richa Tiwari Sunny Jansen Preeti Singh Yun Liu Shekoofeh Azizi Aishwarya Kamath Johan Ferret Shreya Pathak Nino Vieillard Ramona Merhej Sarah Perrin Tatiana Matejovicova Alexandre Ram\u00e9 Morgane Riviere Louis Rouillard Thomas Mesnard Geoffrey Cideron Jean bastien Grill Sabela Ramos Edouard Yvinec Michelle Casbon Elena Buchatskaya Jean-Baptiste Alayrac Dmitry Lepikhin Vlad Feinberg Sebastian Borgeaud Alek Andreev Cassidy Hardin Robert Dadashi L\u00e9onard Hussenot Armand Joulin Olivier Bachem Yossi Matias Katherine Chou Avinatan Hassidim Kavi Goel Clement Farabet Joelle Barral TrisWarkentin Jonathon Shlens David Fleet Victor Cotruta Omar Sanseviero Gus Martins Phoebe Kirk Anand Rao Shravya Shetty David F. Steiner Can Kirmizibayrak Rory Pilgrim Daniel Golden and Lin Yang. 2025. MedGemma Technical Report. arXiv:2507.05201 [cs.AI] https:\/\/arxiv.org\/abs\/2507.05201"},{"key":"e_1_3_2_1_23_1","volume-title":"Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning. In The Thirteenth International Conference on Learning Representations. https: \/\/openreview.net\/forum?id=A6Y7AqlzLW","author":"Setlur Amrith","year":"2025","unstructured":"Amrith Setlur, Chirag Nagpal, Adam Fisch, Xinyang Geng, Jacob Eisenstein, Rishabh Agarwal, Alekh Agarwal, Jonathan Berant, and Aviral Kumar. 2025. Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning. In The Thirteenth International Conference on Learning Representations. https: \/\/openreview.net\/forum?id=A6Y7AqlzLW"},{"key":"e_1_3_2_1_24_1","volume-title":"European Conference on Computer Vision. Springer, 56-73","author":"Sun Yuxuan","year":"2024","unstructured":"Yuxuan Sun, HaoWu, Chenglu Zhu, Sunyi Zheng, Qizi Chen, Kai Zhang, Yunlong Zhang, Dan Wan, Xiaoxiao Lan, Mengyue Zheng, et al. 2024. Pathmmu: A massive multimodal expert-level benchmark for understanding and reasoning in pathology. In European Conference on Computer Vision. Springer, 56-73."},{"key":"e_1_3_2_1_25_1","volume-title":"JudgeBench: A Benchmark for Evaluating LLM-Based Judges. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id= G0dksFayVq","author":"Tan Sijun","year":"2025","unstructured":"Sijun Tan, Siyuan Zhuang, Kyle Montgomery, William Yuan Tang, Alejandro Cuadron, Chenguang Wang, Raluca Popa, and Ion Stoica. 2025. JudgeBench: A Benchmark for Evaluating LLM-Based Judges. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id= G0dksFayVq"},{"key":"e_1_3_2_1_26_1","unstructured":"V Team Wenyi Hong Wenmeng Yu Xiaotao Gu Guo Wang Guobing Gan Haomiao Tang Jiale Cheng Ji Qi Junhui Ji Lihang Pan Shuaiqi Duan Weihan Wang Yan Wang Yean Cheng Zehai He Zhe Su Zhen Yang Ziyang Pan Aohan Zeng Baoxu Wang Bin Chen Boyan Shi Changyu Pang Chenhui Zhang Da Yin Fan Yang Guoqing Chen Jiazheng Xu Jiale Zhu Jiali Chen Jing Chen Jinhao Chen Jinghao Lin Jinjiang Wang Junjie Chen Leqi Lei Letian Gong Leyi Pan Mingdao Liu Mingde Xu Mingzhi Zhang Qinkai Zheng Sheng Yang Shi Zhong Shiyu Huang Shuyuan Zhao Siyan Xue Shangqin Tu Shengbiao Meng Tianshu Zhang Tianwei Luo Tianxiang Hao Tianyu Tong Wenkai Li Wei Jia Xiao Liu Xiaohan Zhang Xin Lyu Xinyue Fan Xuancheng Huang Yanling Wang Yadong Xue Yanfeng Wang Yanzi Wang Yifan An Yifan Du Yiming Shi Yiheng Huang Yilin Niu Yuan Wang Yuanchang Yue Yuchen Li Yutao Zhang Yuting Wang Yu Wang Yuxuan Zhang Zhao Xue Zhenyu Hou Zhengxiao Du Zihan Wang Peng Zhang Debing Liu Bin Xu Juanzi Li Minlie Huang Yuxiao Dong and Jie Tang. 2025. GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning. arXiv:2507.01006 [cs.CV] https:\/\/arxiv.org\/abs\/2507.01006"},{"key":"e_1_3_2_1_27_1","volume-title":"Not Enough: Aligning the Reasoning Process of Reward Models. arXiv preprint arXiv:2602.04649","author":"Wang Binghai","year":"2026","unstructured":"Binghai Wang, Yantao Liu, Yuxuan Liu, Tianyi Tang, Shenzhi Wang, Chang Gao, Chujie Zheng, Yichang Zhang, Le Yu, Shixuan Liu, et al. 2026. Outcome Accuracy is Not Enough: Aligning the Reasoning Process of Reward Models. arXiv preprint arXiv:2602.04649 (2026)."},{"key":"e_1_3_2_1_28_1","volume-title":"GRAM: A Generative Foundation Reward Model for Reward Generalization. In Forty-second International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=rxKC8v2uHc","author":"Gan Yang","year":"2025","unstructured":"ChenglongWang, Yang Gan, Yifu Huo, Yongyu Mu, Qiaozhi He, MuRun Yang, Bei Li, Tong Xiao, Chunliang Zhang, Tongran Liu, and JingBo Zhu. 2025. GRAM: A Generative Foundation Reward Model for Reward Generalization. In Forty-second International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=rxKC8v2uHc"},{"key":"e_1_3_2_1_29_1","volume-title":"Connor Holmes, Samyam Rajbhandari, Olatunji Ruwase, Feng Yan, Lei Yang, and Yuxiong He.","author":"Wang Guanhua","year":"2023","unstructured":"Guanhua Wang, Heyang Qin, Sam Ade Jacobs, Connor Holmes, Samyam Rajbhandari, Olatunji Ruwase, Feng Yan, Lei Yang, and Yuxiong He. 2023. Zero: Extremely efficient collective communication for giant model training. arXiv preprint arXiv:2306.10209 (2023)."},{"key":"e_1_3_2_1_30_1","unstructured":"Weiyun Wang Zhangwei Gao Lixin Gu Hengjun Pu Long Cui Xingguang Wei Zhaoyang Liu Linglin Jing Shenglong Ye Jie Shao et al. 2025. InternVL3.5: Advancing Open-Source Multimodal Models in Versatility Reasoning and Efficiency. arXiv preprint arXiv:2508.18265 (2025)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Xiaokun Wang Peiyu Wang Jiangbo Pei Wei Shen Yi Peng Yunzhuo Hao Weijie Qiu Ai Jian Tianyidan Xie Xuchen Song Yang Liu and Yahui Zhou. 2025. Skywork-VL Reward: An Effective Reward Model for Multimodal Understanding and Reasoning. arXiv:2505.07263 [cs.CV] https:\/\/arxiv.org\/abs\/2505.07263","DOI":"10.18653\/v1\/2025.findings-acl.128"},{"key":"e_1_3_2_1_32_1","volume-title":"Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum? id=1PL1NIMMrw","author":"Wang Xuezhi","year":"2023","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc V Le, Ed H. Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2023. Self-Consistency Improves Chain of Thought Reasoning in Language Models. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum? id=1PL1NIMMrw"},{"key":"e_1_3_2_1_33_1","volume-title":"Unified reward model for multimodal understanding and generation. arXiv preprint arXiv:2503.05236","author":"Wang Yibin","year":"2025","unstructured":"Yibin Wang, Yuhang Zang, Hao Li, Cheng Jin, and Jiaqi Wang. 2025. Unified reward model for multimodal understanding and generation. arXiv preprint arXiv:2503.05236 (2025)."},{"key":"e_1_3_2_1_34_1","volume-title":"J1: Incentivizing thinking in llm-as-a-judge via reinforcement learning. arXiv preprint arXiv:2505.10320","author":"Whitehouse Chenxi","year":"2025","unstructured":"Chenxi Whitehouse, Tianlu Wang, Ping Yu, Xian Li, Jason Weston, Ilia Kulikov, and Swarnadeep Saha. 2025. J1: Incentivizing thinking in llm-as-a-judge via reinforcement learning. arXiv preprint arXiv:2505.10320 (2025)."},{"key":"e_1_3_2_1_35_1","unstructured":"Yangzhen Wu Zhiqing Sun Shanda Li Sean Welleck and Yiming Yang. 2025. Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for LLM Problem-Solving. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=VNckp7JEHn"},{"key":"e_1_3_2_1_36_1","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference. 13618-13628","author":"Xiong Tianyi","year":"2025","unstructured":"Tianyi Xiong, Xiyao Wang, Dong Guo, Qinghao Ye, Haoqi Fan, Quanquan Gu, Heng Huang, and Chunyuan Li. 2025. Llava-critic: Learning to evaluate multimodal models. In Proceedings of the Computer Vision and Pattern Recognition Conference. 13618-13628."},{"key":"e_1_3_2_1_37_1","volume-title":"Multimodal chatgpt for medical applications: an experimental study of gpt-4v. arXiv preprint arXiv:2310.19061","author":"Yan Zhiling","year":"2023","unstructured":"Zhiling Yan, Kai Zhang, Rong Zhou, Lifang He, Xiang Li, and Lichao Sun. 2023. Multimodal chatgpt for medical applications: an experimental study of gpt-4v. arXiv preprint arXiv:2310.19061 (2023)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.837"},{"key":"e_1_3_2_1_39_1","first-page":"10859","article-title":"Huatuogpt, towards taming language model to be a doctor. In Findings of the association for computational linguistics","volume":"2023","author":"Zhang Hongbo","year":"2023","unstructured":"Hongbo Zhang, Junying Chen, Feng Jiang, Fei Yu, Zhihong Chen, Guiming Chen, Jianquan Li, Xiangbo Wu, Zhang Zhiyi, Qingying Xiao, et al. 2023. Huatuogpt, towards taming language model to be a doctor. In Findings of the association for computational linguistics: EMNLP 2023. 10859-10885.","journal-title":"EMNLP"},{"key":"e_1_3_2_1_40_1","volume-title":"RadAgents: Multimodal Agentic Reasoning for Chest X-ray Interpretation with Radiologist-like Workflows. arXiv preprint arXiv:2509.20490","author":"Zhang Kai","year":"2025","unstructured":"Kai Zhang, Corey D Barrett, Jangwon Kim, Lichao Sun, Tara Taghavi, and Krishnaram Kenthapadi. 2025. RadAgents: Multimodal Agentic Reasoning for Chest X-ray Interpretation with Radiologist-like Workflows. arXiv preprint arXiv:2509.20490 (2025)."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.ijcnlp-short.26"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-024-03185-2"},{"key":"e_1_3_2_1_43_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Ccwp4tFEtE","author":"Zhang Lunjun","year":"2025","unstructured":"Lunjun Zhang, Arian Hosseini, Hritik Bansal, Mehran Kazemi, Aviral Kumar, and Rishabh Agarwal. 2025. Generative Verifiers: Reward Modeling as Next-Token Prediction. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Ccwp4tFEtE"},{"key":"e_1_3_2_1_44_1","volume-title":"A comprehensive survey of reward models: Taxonomy, applications, challenges, and future. arXiv preprint arXiv:2504.12328","author":"Zhong Jialun","year":"2025","unstructured":"Jialun Zhong,Wei Shen, Yanzeng Li, Songyang Gao, Hua Lu, Yicheng Chen, Yang Zhang, Wei Zhou, Jinjie Gu, and Lei Zou. 2025. A comprehensive survey of reward models: Taxonomy, applications, challenges, and future. arXiv preprint arXiv:2504.12328 (2025)."},{"key":"e_1_3_2_1_45_1","volume-title":"Medxpertqa: Benchmarking expertlevel medical reasoning and understanding. arXiv preprint arXiv:2501.18362","author":"Zuo Yuxin","year":"2025","unstructured":"Yuxin Zuo, Shang Qu, Yifei Li, Zhangren Chen, Xuekai Zhu, Ermo Hua, Kaiyan Zhang, Ning Ding, and Bowen Zhou. 2025. Medxpertqa: Benchmarking expertlevel medical reasoning and understanding. arXiv preprint arXiv:2501.18362 (2025)."}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:14:45Z","timestamp":1786065285000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3819019"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":45,"alternative-id":["10.1145\/3770855.3819019","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3819019","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}