{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:13Z","timestamp":1786120813185,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":52,"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\/3770855.3818999","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:43Z","timestamp":1786036543000},"page":"13008-13019","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Sci-PRM: A Tool Aware Process Reward Model for Scientific Reasoning Verification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4468-5529","authenticated-orcid":false,"given":"Xiangyu","family":"Zhao","sequence":"first","affiliation":[{"name":"Hong Kong Polytechnic University, Hong Kong, China and Shanghai AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8047-4465","authenticated-orcid":false,"given":"Henry Hengyuan","family":"Zhao","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5844-0920","authenticated-orcid":false,"given":"Yiheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China and Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2627-8318","authenticated-orcid":false,"given":"Wanghan","family":"Xu","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China and Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8074-6416","authenticated-orcid":false,"given":"Yuhao","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Chengdu, China and Sichuan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2742-026X","authenticated-orcid":false,"given":"Qinglong","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China and Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6266-5780","authenticated-orcid":false,"given":"Zhiwang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China and Tongji University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3378-7201","authenticated-orcid":false,"given":"Lei","family":"Bai","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9654-260X","authenticated-orcid":false,"given":"Wenlong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3130-0554","authenticated-orcid":false,"given":"Xiao-Ming","family":"Wu","sequence":"additional","affiliation":[{"name":"Hong Kong Polytechnic University, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Mayank Agarwal Ibrahim Abdelaziz Kinjal Basu Merve Unuvar Luis A. Lastras Yara Rizk and Pavan Kapanipathi. 2026. ToolRM: Outcome Reward Models for Tool-Calling Large Language Models. arXiv:2509.11963 [cs.CL] https:\/\/arxiv.org\/abs\/2509.11963"},{"key":"e_1_3_2_2_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_2_3_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano Christopher Hesse and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arXiv:2110.14168 [cs.LG] https:\/\/arxiv.org\/abs\/2110.14168"},{"key":"e_1_3_2_2_4_1","unstructured":"Guanting Dong Yifei Chen Xiaoxi Li Jiajie Jin Hongjin Qian Yutao Zhu Hangyu Mao Guorui Zhou Zhicheng Dou and Ji-Rong Wen. 2025. Tool-Star: Empowering LLM-Brained Multi-Tool Reasoner via Reinforcement Learning. arXiv:2505.16410 [cs.CL] https:\/\/arxiv.org\/abs\/2505.16410"},{"key":"e_1_3_2_2_5_1","volume-title":"Mol-instructions: A large-scale biomolecular instruction dataset for large language models. arXiv preprint arXiv:2306.08018","author":"Fang Yin","year":"2023","unstructured":"Yin Fang, Xiaozhuan Liang, Ningyu Zhang, Kangwei Liu, Rui Huang, Zhuo Chen, Xiaohui Fan, and Huajun Chen. 2023. Mol-instructions: A large-scale biomolecular instruction dataset for large language models. arXiv preprint arXiv:2306.08018 (2023)."},{"key":"e_1_3_2_2_6_1","volume-title":"Retool: Reinforcement learning for strategic tool use in llms. arXiv preprint arXiv:2504.11536","author":"Feng Jiazhan","year":"2025","unstructured":"Jiazhan Feng, Shijue Huang, Xingwei Qu, Ge Zhang, Yujia Qin, Baoquan Zhong, Chengquan Jiang, Jinxin Chi, and Wanjun Zhong. 2025a. Retool: Reinforcement learning for strategic tool use in llms. arXiv preprint arXiv:2504.11536 (2025)."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.610"},{"key":"e_1_3_2_2_8_1","unstructured":"Google. 2025. Gemini 3. Google DeepMind. https:\/\/aistudio.google.com\/models\/gemini-3"},{"key":"e_1_3_2_2_9_1","volume-title":"CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Sx038qxjek","author":"Gou Zhibin","year":"2024","unstructured":"Zhibin Gou, Zhihong Shao, Yeyun Gong, yelong shen, Yujiu Yang, Nan Duan, and Weizhu Chen. 2024. CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=Sx038qxjek"},{"key":"e_1_3_2_2_10_1","unstructured":"Dong Guo Faming Wu Feida Zhu Fuxing Leng Guang Shi Haobin Chen Haoqi Fan Jian Wang Jianyu Jiang Jiawei Wang et al. 2025. Seed1. 5-vl technical report. arXiv preprint arXiv:2505.07062 (2025)."},{"key":"e_1_3_2_2_11_1","volume-title":"TIM-PRM: Verifying multimodal reasoning with Tool-Integrated PRM. arXiv preprint arXiv:2511.22998","author":"Kuang Peng","year":"2025","unstructured":"Peng Kuang, Xiangxiang Wang, Wentao Liu, Jian Dong, and Kaidi Xu. 2025. TIM-PRM: Verifying multimodal reasoning with Tool-Integrated PRM. arXiv preprint arXiv:2511.22998 (2025)."},{"key":"e_1_3_2_2_12_1","volume-title":"Lingpeng Kong, and Qi Liu.","author":"Li Lei","year":"2025","unstructured":"Lei Li, Yuancheng Wei, Zhihui Xie, Xuqing Yang, Yifan Song, Peiyi Wang, Chenxin An, Tianyu Liu, Sujian Li, Bill Yuchen Lin, Lingpeng Kong, and Qi Liu. 2025b. VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models. In CVPR."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.428"},{"key":"e_1_3_2_2_14_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=v8L0pN6EOi","author":"Lightman Hunter","year":"2024","unstructured":"Hunter Lightman, Vineet Kosaraju, Yuri Burda, Harrison Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2024. Let's Verify Step by Step. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=v8L0pN6EOi"},{"key":"e_1_3_2_2_15_1","volume-title":"SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering. arXiv:2102.09542 [cs.CV] https:\/\/arxiv.org\/abs\/2102.09542","author":"Liu Bo","year":"2021","unstructured":"Bo Liu, Li-Ming Zhan, Li Xu, Lin Ma, Yan Yang, and Xiao-Ming Wu. 2021. SLAKE: A Semantically-Labeled Knowledge-Enhanced Dataset for Medical Visual Question Answering. arXiv:2102.09542 [cs.CV] https:\/\/arxiv.org\/abs\/2102.09542"},{"key":"e_1_3_2_2_16_1","unstructured":"Chris Yuhao Liu Liang Zeng Yuzhen Xiao Jujie He Jiacai Liu Chaojie Wang Rui Yan Wei Shen Fuxiang Zhang Jiacheng Xu et al. 2025b. Skywork-reward-v2: Scaling preference data curation via human-ai synergy. arXiv preprint arXiv:2507.01352 (2025)."},{"key":"e_1_3_2_2_17_1","volume-title":"BioProBench: Comprehensive Dataset and Benchmark in Biological Protocol Understanding and Reasoning. arXiv preprint arXiv:2505.07889","author":"Liu Yuyang","year":"2025","unstructured":"Yuyang Liu, Liuzhenghao Lv, Xiancheng Zhang, Li Yuan, and Yonghong Tian. 2025a. BioProBench: Comprehensive Dataset and Benchmark in Biological Protocol Understanding and Reasoning. arXiv preprint arXiv:2505.07889 (2025)."},{"key":"e_1_3_2_2_18_1","volume-title":"Apigen: Automated pipeline for generating verifiable and diverse function-calling datasets. Advances in Neural Information Processing Systems, V37","author":"Liu Zuxin","year":"2024","unstructured":"Zuxin Liu, Thai Hoang, Jianguo Zhang, Ming Zhu, Tian Lan, Juntao Tan, Weiran Yao, Zhiwei Liu, Yihao Feng, Rithesh RN, et al., 2024. Apigen: Automated pipeline for generating verifiable and diverse function-calling datasets. Advances in Neural Information Processing Systems, V37 (2024), 54463-54482."},{"key":"e_1_3_2_2_19_1","unstructured":"LLaMA team. 2024. Llama 3.2: Revolutionizing edge AI and vision with open customizable models. LLaMA team. https:\/\/ai.meta.com\/blog\/llama-3-2-connect-2024-vision-edge-mobile-devices"},{"key":"e_1_3_2_2_20_1","volume-title":"Benedict Emoekabu, Aswanth Krishnan, Tanya Gupta, Mara Schilling-Wilhelmi, Macjonathan Okereke, Anagha Aneesh, et al.","author":"Mirza Adrian","year":"2024","unstructured":"Adrian Mirza, Nawaf Alampara, Sreekanth Kunchapu, Marti no R\u00edos-Garc\u00eda, Benedict Emoekabu, Aswanth Krishnan, Tanya Gupta, Mara Schilling-Wilhelmi, Macjonathan Okereke, Anagha Aneesh, et al., 2024. Are large language models superhuman chemists? arXiv preprint arXiv:2404.01475 (2024)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"Long Ouyang Jeff Wu Xu Jiang Diogo Almeida Carroll L. Wainwright Pamela Mishkin Chong Zhang Sandhini Agarwal Katarina Slama Alex Ray John Schulman Jacob Hilton Fraser Kelton Luke Miller Maddie Simens Amanda Askell Peter Welinder Paul Christiano Jan Leike and Ryan Lowe. 2022. Training language models to follow instructions with human feedback. arXiv:2203.02155 [cs.CL] https:\/\/arxiv.org\/abs\/2203.02155","DOI":"10.52202\/068431-2011"},{"key":"e_1_3_2_2_22_1","volume-title":"Amrit Singh Bedi, and Dinesh Manocha","author":"Patel Bhrij","year":"2024","unstructured":"Bhrij Patel, Souradip Chakraborty, Wesley A. Suttle, Mengdi Wang, Amrit Singh Bedi, and Dinesh Manocha. 2024. AIME: AI System Optimization via Multiple LLM Evaluators. arXiv:2410.03131 [cs.AI] https:\/\/arxiv.org\/abs\/2410.03131"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.52202\/085713-3524"},{"key":"e_1_3_2_2_24_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=dHng2O0Jjr","author":"Qin Yujia","year":"2024","unstructured":"Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Lauren Hong, Runchu Tian, Ruobing Xie, Jie Zhou, Mark Gerstein, dahai li, Zhiyuan Liu, and Maosong Sun. 2024. ToolLLM: Facilitating Large Language Models to Master 16000 Real-world APIs. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=dHng2O0Jjr"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2997"},{"key":"e_1_3_2_2_26_1","unstructured":"John Schulman Filip Wolski Prafulla Dhariwal Alec Radford and Oleg Klimov. 2017. Proximal Policy Optimization Algorithms. arXiv:1707.06347 [cs.LG] https:\/\/arxiv.org\/abs\/1707.06347"},{"key":"e_1_3_2_2_27_1","unstructured":"Zhihong Shao Peiyi Wang Qihao Zhu Runxin Xu Junxiao Song Xiao Bi Haowei Zhang Mingchuan Zhang Y. K. Li Y. Wu and Daya Guo. 2024. DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models. arXiv:2402.03300 [cs.CL] https:\/\/arxiv.org\/abs\/2402.03300"},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-main.679"},{"key":"e_1_3_2_2_29_1","unstructured":"Aaditya Singh Adam Fry Adam Perelman Adam Tart Adi Ganesh Ahmed El-Kishky Aidan McLaughlin Aiden Low AJ Ostrow Akhila Ananthram et al. 2025. Openai gpt-5 system card. arXiv preprint arXiv:2601.03267 (2025)."},{"key":"e_1_3_2_2_30_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=4FWAwZtd2n","author":"Snell Charlie Victor","year":"2025","unstructured":"Charlie Victor Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2025. Scaling LLM Test-Time Compute Optimally Can be More Effective than Scaling Parameters for Reasoning. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=4FWAwZtd2n"},{"key":"e_1_3_2_2_31_1","unstructured":"Jonathan Uesato Nate Kushman Ramana Kumar Francis Song Noah Siegel Lisa Wang Antonia Creswell Geoffrey Irving and Irina Higgins. 2022. Solving math word problems with process- and outcome-based feedback. arXiv:2211.14275 [cs.LG] https:\/\/arxiv.org\/abs\/2211.14275"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.510"},{"key":"e_1_3_2_2_33_1","unstructured":"Weiyun Wang Zhangwei Gao Lianjie Chen Zhe Chen Jinguo Zhu Xiangyu Zhao Yangzhou Liu Yue Cao Shenglong Ye Xizhou Zhu et al. 2025. VisualPRM: An Effective Process Reward Model for Multimodal Reasoning. arXiv preprint arXiv:2503.10291 (2025)."},{"key":"e_1_3_2_2_34_1","volume-title":"The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=xJljiPE6dg","author":"Wen Jiaxin","year":"2025","unstructured":"Jiaxin Wen, Ruiqi Zhong, Akbir Khan, Ethan Perez, Jacob Steinhardt, Minlie Huang, Samuel R. Bowman, He He, and Shi Feng. 2025. Language Models Learn to Mislead Humans via RLHF. In The Thirteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=xJljiPE6dg"},{"key":"e_1_3_2_2_35_1","volume-title":"Reward Hacking in Reinforcement Learning. lilianweng.github.io (Nov","author":"Weng Lilian","year":"2024","unstructured":"Lilian Weng. 2024. Reward Hacking in Reinforcement Learning. lilianweng.github.io (Nov 2024). https:\/\/lilianweng.github.io\/posts\/2024-11-28-reward-hacking\/"},{"key":"e_1_3_2_2_36_1","unstructured":"Feijie Wu Weiwu Zhu Yuxiang Zhang Soumya Chatterjee Jiarong Zhu Fan Mo Rodin Luo and Jing Gao. 2025. PORTool: Tool-Use LLM Training with Rewarded Tree. arXiv:2510.26020 [cs.CL] https:\/\/arxiv.org\/abs\/2510.26020"},{"key":"e_1_3_2_2_37_1","unstructured":"Zhiheng Xi Chenyang Liao Guanyu Li Yajie Yang Wenxiang Chen Zhihao Zhang Binghai Wang Senjie Jin Yuhao Zhou Jian Guan Wei Wu Tao Ji Tao Gui Qi Zhang and Xuanjing Huang. 2025. AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress. arXiv:2511.08325 [cs.CL] https:\/\/arxiv.org\/abs\/2511.08325"},{"key":"e_1_3_2_2_38_1","unstructured":"Wanghan Xu Yuhao Zhou Yifan Zhou Qinglong Cao Shuo Li Jia Bu Bo Liu Yixin Chen Xuming He Xiangyu Zhao et al. 2025. Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows. arXiv preprint arXiv:2512.16969 (2025)."},{"key":"e_1_3_2_2_39_1","unstructured":"An Yang Anfeng Li Baosong Yang Beichen Zhang Binyuan Hui Bo Zheng Bowen Yu Chang Gao Chengen Huang Chenxu Lv Chujie Zheng Dayiheng Liu Fan Zhou Fei Huang Feng Hu Hao Ge Haoran Wei Huan Lin Jialong Tang Jian Yang Jianhong Tu Jianwei Zhang Jianxin Yang Jiaxi Yang Jing Zhou Jingren Zhou Junyang Lin Kai Dang Keqin Bao Kexin Yang Le Yu Lianghao Deng Mei Li Mingfeng Xue Mingze Li Pei Zhang Peng Wang Qin Zhu Rui Men Ruize Gao Shixuan Liu Shuang Luo Tianhao Li Tianyi Tang Wenbiao Yin Xingzhang Ren Xinyu Wang Xinyu Zhang Xuancheng Ren Yang Fan Yang Su Yichang Zhang Yinger Zhang Yu Wan Yuqiong Liu Zekun Wang Zeyu Cui Zhenru Zhang Zhipeng Zhou and Zihan Qiu. 2025. Qwen3 Technical Report. arXiv:2505.09388 [cs.CL] https:\/\/arxiv.org\/abs\/2505.09388"},{"key":"e_1_3_2_2_40_1","unstructured":"An Yang Beichen Zhang Binyuan Hui Bofei Gao Bowen Yu Chengpeng Li Dayiheng Liu Jianhong Tu Jingren Zhou Junyang Lin Keming Lu Mingfeng Xue Runji Lin Tianyu Liu Xingzhang Ren and Zhenru Zhang. 2024. Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement. arXiv:2409.12122 [cs.CL] https:\/\/arxiv.org\/abs\/2409.12122"},{"key":"e_1_3_2_2_41_1","volume-title":"DAPO: An Open-Source LLM Reinforcement Learning System at Scale. arXiv:2503.14476 [cs.LG] https:\/\/arxiv.org\/abs\/2503.14476","author":"Yu Qiying","year":"2025","unstructured":"Qiying Yu, Zheng Zhang, Ruofei Zhu, Yufeng Yuan, Xiaochen Zuo, Yu Yue, Weinan Dai, 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, Yuxuan Song, Xiangpeng Wei, Hao Zhou, Jingjing Liu, Wei-Ying Ma, Ya-Qin Zhang, Lin Yan, Mu Qiao, Yonghui Wu, and Mingxuan Wang. 2025. DAPO: An Open-Source LLM Reinforcement Learning System at Scale. arXiv:2503.14476 [cs.LG] https:\/\/arxiv.org\/abs\/2503.14476"},{"key":"e_1_3_2_2_42_1","volume-title":"Wenxuan Wang, Wenxiang Jiao, and Pinjia He.","author":"Yuan Youliang","year":"2025","unstructured":"Youliang Yuan, Qiuyang Mang, Jingbang Chen, Hong Wan, Xiaoyuan Liu, Junjielong Xu, Jen tse Huang, Wenxuan Wang, Wenxiang Jiao, and Pinjia He. 2025. Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards. arXiv:2510.07774 [cs.CL] https:\/\/arxiv.org\/abs\/2510.07774"},{"key":"e_1_3_2_2_43_1","unstructured":"Aohan Zeng Xin Lv Qinkai Zheng Zhenyu Hou Bin Chen Chengxing Xie Cunxiang Wang Da Yin Hao Zeng Jiajie Zhang et al. 2025. Glm-4.5: Agentic reasoning and coding (arc) foundation models. arXiv preprint arXiv:2508.06471 (2025)."},{"key":"e_1_3_2_2_44_1","unstructured":"Di Zhang Wei Liu Qian Tan Jingdan Chen Hang Yan Yuliang Yan Jiatong Li Weiran Huang Xiangyu Yue Dongzhan Zhou Shufei Zhang Mao Su Hansen Zhong Yuqiang Li and Wanli Ouyang. 2024. ChemLLM: A Chemical Large Language Model. arXiv:2402.06852 [cs.AI]"},{"key":"e_1_3_2_2_45_1","volume-title":"Compassjudger-2: Towards generalist judge model via verifiable rewards. arXiv preprint arXiv:2507.09104","author":"Zhang Taolin","year":"2025","unstructured":"Taolin Zhang, Maosong Cao, Alexander Lam, Songyang Zhang, and Kai Chen. 2025a. Compassjudger-2: Towards generalist judge model via verifiable rewards. arXiv preprint arXiv:2507.09104 (2025)."},{"key":"e_1_3_2_2_46_1","unstructured":"Yi-Fan Zhang Haihua Yang Huanyu Zhang Yang Shi Zezhou Chen Haochen Tian Chaoyou Fu Haotian Wang Kai Wu Bo Cui Xu Wang Jianfei Pan Haotian Wang Zhang Zhang and Liang Wang. 2025b. BaseReward: A Strong Baseline for Multimodal Reward Model. arXiv:2509.16127 [cs.CV] https:\/\/arxiv.org\/abs\/2509.16127"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.547"},{"key":"e_1_3_2_2_48_1","volume-title":"MSEarth: A Benchmark for Multimodal Scientific Comprehension of Earth Science. arXiv preprint arXiv:2505.20740","author":"Zhao Xiangyu","year":"2025","unstructured":"Xiangyu Zhao, Wanghan Xu, Bo Liu, Yuhao Zhou, Fenghua Ling, Ben Fei, Xiaoyu Yue, Lei Bai, Wenlong Zhang, and Xiao-Ming Wu. 2025a. MSEarth: A Benchmark for Multimodal Scientific Comprehension of Earth Science. arXiv preprint arXiv:2505.20740 (2025)."},{"key":"e_1_3_2_2_49_1","unstructured":"Xiangyu Zhao Wanghan Xu Bo Liu Yuhao Zhou Fenghua Ling Ben Fei Xiaoyu Yue Lei Bai Wenlong Zhang and Xiao-Ming Wu. 2025b. MSEarth: A Multimodal Scientific Dataset and Benchmark for Phenomena Uncovering in Earth Science. arXiv:2505.20740 [cs.AI] https:\/\/arxiv.org\/abs\/2505.20740"},{"key":"e_1_3_2_2_50_1","volume-title":"Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track. https:\/\/openreview.net\/forum?id=uccHPGDlao","author":"Zheng Lianmin","year":"2023","unstructured":"Lianmin Zheng, Wei-Lin Chiang, Ying Sheng, Siyuan Zhuang, Zhanghao Wu, Yonghao Zhuang, Zi Lin, Zhuohan Li, Dacheng Li, Eric Xing, Hao Zhang, Joseph E. Gonzalez, and Ion Stoica. 2023. Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena. In Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track. https:\/\/openreview.net\/forum?id=uccHPGDlao"},{"key":"e_1_3_2_2_51_1","volume-title":"Sci-verifier: Scientific verifier with thinking. arXiv preprint arXiv:2509.24285","author":"Zheng Shenghe","year":"2025","unstructured":"Shenghe Zheng, Chenyu Huang, Fangchen Yu, Junchi Yao, Jingqi Ye, Tao Chen, Yun Luo, Ning Ding, Lei Bai, Ganqu Cui, et al., 2025. Sci-verifier: Scientific verifier with thinking. arXiv preprint arXiv:2509.24285 (2025)."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"crossref","unstructured":"Jiaru Zou Ling Yang Jingwen Gu Jiahao Qiu Ke Shen Jingrui He and Mengdi Wang. 2025. ReasonFlux-PRM: Trajectory-Aware PRMs for Long Chain-of-Thought Reasoning in LLMs. In The Thirty-ninth Annual Conference on Neural Information Processing Systems. https:\/\/openreview.net\/forum?id=f3sZjkQbv2","DOI":"10.52202\/085713-0901"}],"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":"2026-08-07T01:28:54Z","timestamp":1786066134000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3818999"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":52,"alternative-id":["10.1145\/3770855.3818999","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3818999","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"}}]}}