{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:24:45Z","timestamp":1787689485118,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":67,"publisher":"ACM","funder":[{"name":"Shanghai Municipal Natural Science Foundation","award":["23ZR1425400"],"award-info":[{"award-number":["23ZR1425400"]}]},{"name":"Shanghai Soft Science Project","award":["25692114700"],"award-info":[{"award-number":["25692114700"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780168","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"1378-1389","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AURORA: Automated Training Framework of Universal Process Reward Models via Ensemble Prompting and Reverse Verification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3555-7143","authenticated-orcid":false,"given":"Xiaoyu","family":"Tan","sequence":"first","affiliation":[{"name":"Tencent Youtu Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8236-7653","authenticated-orcid":false,"given":"Tianchu","family":"Yao","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4246-9106","authenticated-orcid":false,"given":"Chao","family":"Qu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1374-1524","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai University of Engineering Science, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-0474-5467","authenticated-orcid":false,"given":"Minghao","family":"Yang","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4937-0805","authenticated-orcid":false,"given":"Dakuan","family":"Lu","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9299-6305","authenticated-orcid":false,"given":"Haozhe","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7346-2794","authenticated-orcid":false,"given":"Xu","family":"Yinghui","sequence":"additional","affiliation":[{"name":"Fudan University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4024-925X","authenticated-orcid":false,"given":"Xihe","family":"Qiu","sequence":"additional","affiliation":[{"name":"Shanghai University of Engineering Science, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Yi: Open Foundation Models by 01.AI. arXiv:2403.04652 [cs.CL]","author":"Young Alex","year":"2024","unstructured":"01. AI:, Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, Heng Li, Jiangcheng Zhu, Jianqun Chen, Jing Chang, Kaidong Yu, Peng Liu, Qiang Liu, Shawn Yue, Senbin Yang, Shiming Yang, Tao Yu, Wen Xie, Wenhao Huang, Xiaohui Hu, Xiaoyi Ren, Xinyao Niu, Pengcheng Nie, Yuchi Xu, Yudong Liu, Yue Wang, Yuxuan Cai, Zhenyu Gu, Zhiyuan Liu, and Zonghong Dai. 2024. Yi: Open Foundation Models by 01.AI. arXiv:2403.04652 [cs.CL]"},{"key":"e_1_3_2_2_2_1","volume-title":"Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems","author":"Berthelot David","year":"2019","unstructured":"David Berthelot, Nicholas Carlini, Ian Goodfellow, Nicolas Papernot, Avital Oliver, and Colin A Raffel. 2019. Mixmatch: A holistic approach to semi-supervised learning. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"e_1_3_2_2_4_1","unstructured":"Boxi Cao Keming Lu Xinyu Lu Jiawei Chen Mengjie Ren Hao Xiang Peilin Liu Yaojie Lu Ben He Xianpei Han et al. 2024. Towards Scalable Automated Alignment of LLMs: A Survey. arXiv preprint arXiv:2406.01252 (2024)."},{"key":"e_1_3_2_2_5_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et al. 2021a. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_2_6_1","volume-title":"Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:2110.14168","author":"Cobbe Karl","year":"2021","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. 2021b. Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_2_7_1","volume-title":"International conference on computers and games. Springer, 72-83","author":"Coulom R\u00e9mi","year":"2006","unstructured":"R\u00e9mi Coulom. 2006. Efficient selectivity and backup operators in Monte-Carlo tree search. In International conference on computers and games. Springer, 72-83."},{"key":"e_1_3_2_2_8_1","volume-title":"Why can gpt learn in-context? language models implicitly perform gradient descent as meta-optimizers. arXiv preprint arXiv:2212.10559","author":"Dai Damai","year":"2022","unstructured":"Damai Dai, Yutao Sun, Li Dong, Yaru Hao, Shuming Ma, Zhifang Sui, and Furu Wei. 2022. Why can gpt learn in-context? language models implicitly perform gradient descent as meta-optimizers. arXiv preprint arXiv:2212.10559 (2022)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"e_1_3_2_2_10_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_2_11_1","volume-title":"The Eleventh International Conference on Learning Representations.","author":"Fu Yao","year":"2022","unstructured":"Yao Fu, Hao Peng, Ashish Sabharwal, Peter Clark, and Tushar Khot. 2022. Complexity-based prompting for multi-step reasoning. In The Eleventh International Conference on Learning Representations."},{"key":"e_1_3_2_2_12_1","volume-title":"Tora: A tool-integrated reasoning agent for mathematical problem solving. arXiv preprint arXiv:2309.17452","author":"Gou Zhibin","year":"2023","unstructured":"Zhibin Gou, Zhihong Shao, Yeyun Gong, Yelong Shen, Yujiu Yang, Minlie Huang, Nan Duan, and Weizhu Chen. 2023. Tora: A tool-integrated reasoning agent for mathematical problem solving. arXiv preprint arXiv:2309.17452 (2023)."},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCC.2012.2218595"},{"key":"e_1_3_2_2_14_1","volume-title":"Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, and Maosong Sun.","author":"He Chaoqun","year":"2024","unstructured":"Chaoqun He, Renjie Luo, Yuzhuo Bai, Shengding Hu, Zhen Leng Thai, Junhao Shen, Jinyi Hu, Xu Han, Yujie Huang, Yuxiang Zhang, Jie Liu, Lei Qi, Zhiyuan Liu, and Maosong Sun. 2024. OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems. arXiv:2402.14008 [cs.CL] https:\/\/arxiv.org\/abs\/2402.14008"},{"key":"e_1_3_2_2_15_1","volume-title":"Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:2103.03874","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021a. Measuring mathematical problem solving with the math dataset. arXiv preprint arXiv:2103.03874 (2021)."},{"key":"e_1_3_2_2_16_1","volume-title":"Measuring Mathematical Problem Solving With the MATH Dataset. NeurIPS","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021b. Measuring Mathematical Problem Solving With the MATH Dataset. NeurIPS (2021)."},{"key":"e_1_3_2_2_17_1","unstructured":"INF-Team. 2024. INF's Open-Source Large Language Models. (2024). https:\/\/github.com\/infly-ai\/INF-LLM"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.123"},{"key":"e_1_3_2_2_19_1","volume-title":"The impact of reasoning step length on large language models. arXiv preprint arXiv:2401.04925","author":"Jin Mingyu","year":"2024","unstructured":"Mingyu Jin, Qinkai Yu, Dong Shu, Haiyan Zhao, Wenyue Hua, Yanda Meng, Yongfeng Zhang, and Mengnan Du. 2024. The impact of reasoning step length on large language models. arXiv preprint arXiv:2401.04925 (2024)."},{"key":"e_1_3_2_2_20_1","volume-title":"Challenges and applications of large language models. arXiv preprint arXiv:2307.10169","author":"Kaddour Jean","year":"2023","unstructured":"Jean Kaddour, Joshua Harris, Maximilian Mozes, Herbie Bradley, Roberta Raileanu, and Robert McHardy. 2023. Challenges and applications of large language models. arXiv preprint arXiv:2307.10169 (2023)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645611"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/11871842_29"},{"key":"e_1_3_2_2_23_1","volume-title":"Numinamath: The largest public dataset in ai4maths with 860k pairs of competition math problems and solutions. Hugging Face repository","author":"Li Jia","year":"2024","unstructured":"Jia Li, Edward Beeching, Lewis Tunstall, Ben Lipkin, Roman Soletskyi, Shengyi Huang, Kashif Rasul, Longhui Yu, Albert Q Jiang, Ziju Shen, et al., 2024. Numinamath: The largest public dataset in ai4maths with 860k pairs of competition math problems and solutions. Hugging Face repository, Vol. 13 (2024)."},{"key":"e_1_3_2_2_24_1","volume-title":"Let's verify step by step. arXiv preprint arXiv:2305.20050","author":"Lightman Hunter","year":"2023","unstructured":"Hunter Lightman, Vineet Kosaraju, Yura Burda, Harri Edwards, Bowen Baker, Teddy Lee, Jan Leike, John Schulman, Ilya Sutskever, and Karl Cobbe. 2023. Let's verify step by step. arXiv preprint arXiv:2305.20050 (2023)."},{"key":"e_1_3_2_2_25_1","volume-title":"Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct. arXiv preprint arXiv:2308.09583","author":"Luo Haipeng","year":"2023","unstructured":"Haipeng Luo, Qingfeng Sun, Can Xu, Pu Zhao, Jianguang Lou, Chongyang Tao, Xiubo Geng, Qingwei Lin, Shifeng Chen, and Dongmei Zhang. 2023. Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct. arXiv preprint arXiv:2308.09583 (2023)."},{"key":"e_1_3_2_2_26_1","unstructured":"Liangchen Luo Yinxiao Liu Rosanne Liu Samrat Phatale Harsh Lara Yunxuan Li Lei Shu Yun Zhu Lei Meng Jiao Sun et al. 2024. Improve Mathematical Reasoning in Language Models by Automated Process Supervision. arXiv preprint arXiv:2406.06592 (2024)."},{"key":"e_1_3_2_2_27_1","volume-title":"Juan Felipe Ceron Uribe, Evgenia Nitishinskaya, Maja Trebacz, and Jan Leike.","author":"McAleese Nat","year":"2024","unstructured":"Nat McAleese, Rai Michael Pokorny, Juan Felipe Ceron Uribe, Evgenia Nitishinskaya, Maja Trebacz, and Jan Leike. 2024. Llm critics help catch llm bugs. arXiv preprint arXiv:2407.00215 (2024)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2191"},{"key":"e_1_3_2_2_29_1","unstructured":"INF o1 Team. 2024. INF-o1 ((\u03c0_0)): Initiating the Journey to the Infinity of LLM Reasoning. https:\/\/inftech-pi-zero.github.io\/ Accessed: 2024-12-31."},{"key":"e_1_3_2_2_30_1","volume-title":"American Invitational Mathematics Examination - AIME","author":"Mathematical Association of America. 2024.","year":"2024","unstructured":"Mathematical Association of America. 2024. American Invitational Mathematics Examination - AIME 2024. https:\/\/maa.org\/math-competitions\/american-invitational-mathematics-examination-aime"},{"key":"e_1_3_2_2_31_1","volume-title":"Gpt-4 technical report. arXiv preprint arXiv:2303.08774","author":"AI.","year":"2023","unstructured":"OpenAI. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_2_32_1","unstructured":"OpenAI. 2024a. Learning to reason with LLMs. https:\/\/openai.com\/index\/learning-to-reason-with-llms\/"},{"key":"e_1_3_2_2_33_1","unstructured":"OpenAI. 2024b. Openai-o1-mini: Advancing cost efficient reasoning. https:\/\/openai.com\/index\/openai-o1-mini-advancing-cost-efficient-reasoning\/"},{"key":"e_1_3_2_2_34_1","volume-title":"Let's Reinforce Step by Step. arXiv preprint arXiv:2311.05821","author":"Pan Sarah","year":"2023","unstructured":"Sarah Pan, Vladislav Lialin, Sherin Muckatira, and Anna Rumshisky. 2023. Let's Reinforce Step by Step. arXiv preprint arXiv:2311.05821 (2023)."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_2_2_36_1","volume-title":"Qwq: Reflect deeply on the boundaries of the unknown. https:\/\/qwenlm.github.io\/blog\/qwq-32b-preview\/","author":"Qwen Team","year":"2024","unstructured":"Team Qwen. 2024. Qwq: Reflect deeply on the boundaries of the unknown. https:\/\/qwenlm.github.io\/blog\/qwq-32b-preview\/"},{"key":"e_1_3_2_2_37_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Shinn Noah","year":"2024","unstructured":"Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2024. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_38_1","unstructured":"Skywork. 2024. Skywork-o1 Open Series. https:\/\/huggingface.co\/Skywork. https:\/\/huggingface.co\/Skywork"},{"key":"e_1_3_2_2_39_1","volume-title":"Scaling llm test-time compute optimally can be more effective than scaling model parameters. arXiv preprint arXiv:2408.03314","author":"Snell Charlie","year":"2024","unstructured":"Charlie Snell, Jaehoon Lee, Kelvin Xu, and Aviral Kumar. 2024. Scaling llm test-time compute optimally can be more effective than scaling model parameters. arXiv preprint arXiv:2408.03314 (2024)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10228-y"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701716.3715247"},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of the 2023 conference on empirical methods in natural language processing: industry track. 650-662","author":"Tan Xiaoyu","year":"2023","unstructured":"Xiaoyu Tan, Shaojie Shi, Xihe Qiu, Chao Qu, Zhenting Qi, Yinghui Xu, and Yuan Qi. 2023. Self-criticism: Aligning large language models with their understanding of helpfulness, honesty, and harmlessness. In Proceedings of the 2023 conference on empirical methods in natural language processing: industry track. 650-662."},{"key":"e_1_3_2_2_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709381"},{"key":"e_1_3_2_2_44_1","unstructured":"Qwen Team. 2024. Qwen2.5: A Party of Foundation Models. https:\/\/qwenlm.github.io\/blog\/qwen2.5\/"},{"key":"e_1_3_2_2_45_1","volume-title":"Solving math word problems with process-and outcome-based feedback. arXiv preprint arXiv:2211.14275","author":"Uesato Jonathan","year":"2022","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 preprint arXiv:2211.14275 (2022)."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.510"},{"key":"e_1_3_2_2_47_1","volume-title":"Aakanksha Chowdhery, and Denny Zhou.","author":"Wang Xuezhi","year":"2022","unstructured":"Xuezhi Wang, Jason Wei, Dale Schuurmans, Quoc Le, Ed Chi, Sharan Narang, Aakanksha Chowdhery, and Denny Zhou. 2022. Self-consistency improves chain of thought reasoning in language models. arXiv preprint arXiv:2203.11171 (2022)."},{"key":"e_1_3_2_2_48_1","unstructured":"Jason Wei Yi Tay Rishi Bommasani Colin Raffel Barret Zoph Sebastian Borgeaud Dani Yogatama Maarten Bosma Denny Zhou Donald Metzler et al. 2022a. Emergent abilities of large language models. arXiv preprint arXiv:2206.07682 (2022)."},{"key":"e_1_3_2_2_49_1","volume-title":"Denny Zhou, et al.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, Fei Xia, Ed Chi, Quoc V Le, Denny Zhou, et al., 2022b. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems, Vol. 35 (2022), 24824-24837."},{"key":"e_1_3_2_2_50_1","volume-title":"Skywork: A more open bilingual foundation model. arXiv preprint arXiv:2310.19341","author":"Wei Tianwen","year":"2023","unstructured":"Tianwen Wei, Liang Zhao, Lichang Zhang, Bo Zhu, Lijie Wang, Haihua Yang, Biye Li, Cheng Cheng, Weiwei L\u00fc, Rui Hu, et al., 2023. Skywork: A more open bilingual foundation model. arXiv preprint arXiv:2310.19341 (2023)."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2574"},{"key":"e_1_3_2_2_52_1","unstructured":"Wei Xiong Chengshuai Shi Jiaming Shen Aviv Rosenberg Zhen Qin Daniele Calandriello Misha Khalman Rishabh Joshi Bilal Piot Mohammad Saleh et al. 2024a. Building math agents with multi-turn iterative preference learning. arXiv preprint arXiv:2409.02392 (2024)."},{"key":"e_1_3_2_2_53_1","unstructured":"Wei Xiong Hanning Zhang Nan Jiang and Tong Zhang. 2024b. An Implementation of Generative PRM. https:\/\/github.com\/RLHFlow\/RLHF-Reward-Modeling."},{"key":"e_1_3_2_2_54_1","unstructured":"Wei Xiong Hanning Zhang Nan Jiang and Tong Zhang. 2024c. RLHFlow\/Llama3.1-8B-PRM-Mistral-Data. https:\/\/huggingface.co\/RLHFlow\/Llama3.1-8B-PRM-Mistral-Data."},{"key":"e_1_3_2_2_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.871"},{"key":"e_1_3_2_2_56_1","volume-title":"Toward Mathematical Expert Model via Self-Improvement. arXiv preprint arXiv:2409.12122","author":"Yang An","year":"2024","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 preprint arXiv:2409.12122 (2024)."},{"key":"e_1_3_2_2_57_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yao Shunyu","year":"2024","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2024. Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_58_1","volume-title":"Outcome-supervised verifiers for planning in mathematical reasoning. arXiv preprint arXiv:2311.09724","author":"Yu Fei","year":"2023","unstructured":"Fei Yu, Anningzhe Gao, and Benyou Wang. 2023a. Outcome-supervised verifiers for planning in mathematical reasoning. arXiv preprint arXiv:2311.09724 (2023)."},{"key":"e_1_3_2_2_59_1","volume-title":"Metamath: Bootstrap your own mathematical questions for large language models. arXiv preprint arXiv:2309.12284","author":"Yu Longhui","year":"2023","unstructured":"Longhui Yu, Weisen Jiang, Han Shi, Jincheng Yu, Zhengying Liu, Yu Zhang, James T Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu. 2023b. Metamath: Bootstrap your own mathematical questions for large language models. arXiv preprint arXiv:2309.12284 (2023)."},{"key":"e_1_3_2_2_60_1","volume-title":"Mammoth: Building math generalist models through hybrid instruction tuning. arXiv preprint arXiv:2309.05653","author":"Yue Xiang","year":"2023","unstructured":"Xiang Yue, Xingwei Qu, Ge Zhang, Yao Fu, Wenhao Huang, Huan Sun, Yu Su, and Wenhu Chen. 2023. Mammoth: Building math generalist models through hybrid instruction tuning. arXiv preprint arXiv:2309.05653 (2023)."},{"key":"e_1_3_2_2_61_1","volume-title":"What and how does in-context learning learn? bayesian model averaging, parameterization, and generalization. arXiv preprint arXiv:2305.19420","author":"Zhang Yufeng","year":"2023","unstructured":"Yufeng Zhang, Fengzhuo Zhang, Zhuoran Yang, and Zhaoran Wang. 2023. What and how does in-context learning learn? bayesian model averaging, parameterization, and generalization. arXiv preprint arXiv:2305.19420 (2023)."},{"key":"e_1_3_2_2_62_1","volume-title":"The Lessons of Developing Process Reward Models in Mathematical Reasoning. arXiv preprint arXiv:2501.07301","author":"Zhang Zhenru","year":"2025","unstructured":"Zhenru Zhang, Chujie Zheng, Yangzhen Wu, Beichen Zhang, Runji Lin, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin. 2025. The Lessons of Developing Process Reward Models in Mathematical Reasoning. arXiv preprint arXiv:2501.07301 (2025)."},{"key":"e_1_3_2_2_63_1","volume-title":"Wee Sun Lee, and David Hsu","author":"Zhao Zirui","year":"2024","unstructured":"Zirui Zhao, Wee Sun Lee, and David Hsu. 2024. Large language models as commonsense knowledge for large-scale task planning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_64_1","volume-title":"Processbench: Identifying process errors in mathematical reasoning. arXiv preprint arXiv:2412.06559","author":"Zheng Chujie","year":"2024","unstructured":"Chujie Zheng, Zhenru Zhang, Beichen Zhang, Runji Lin, Keming Lu, Bowen Yu, Dayiheng Liu, Jingren Zhou, and Junyang Lin. 2024. Processbench: Identifying process errors in mathematical reasoning. arXiv preprint arXiv:2412.06559 (2024)."},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2020"},{"key":"e_1_3_2_2_66_1","volume-title":"Is your model really a good math reasoner? evaluating mathematical reasoning with checklist. arXiv preprint arXiv:2407.08733","author":"Zhou Zihao","year":"2024","unstructured":"Zihao Zhou, Shudong Liu, Maizhen Ning, Wei Liu, Jindong Wang, Derek F Wong, Xiaowei Huang, Qiufeng Wang, and Kaizhu Huang. 2024. Is your model really a good math reasoner? evaluating mathematical reasoning with checklist. arXiv preprint arXiv:2407.08733 (2024)."},{"key":"e_1_3_2_2_67_1","unstructured":"Qihao Zhu Daya Guo Zhihong Shao Dejian Yang Peiyi Wang Runxin Xu Y Wu Yukun Li Huazuo Gao Shirong Ma et al. 2024. DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code Intelligence. arXiv preprint arXiv:2406.11931 (2024)."}],"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.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780168","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:05:34Z","timestamp":1787688334000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780168"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":67,"alternative-id":["10.1145\/3770854.3780168","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780168","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}