{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T01:45:23Z","timestamp":1787017523352,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3760944","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T00:36:36Z","timestamp":1762562196000},"page":"4665-4669","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Arrows of Math Reasoning Data Synthesis for Large Language Models: Diversity, Complexity and Correctness"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-5652-7970","authenticated-orcid":false,"given":"Sirui","family":"Chen","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3013-9439","authenticated-orcid":false,"given":"Changxin","family":"Tian","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2505-1619","authenticated-orcid":false,"given":"Binbin","family":"Hu","sequence":"additional","affiliation":[{"name":"Ant Group, Hang Zhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-0961-1479","authenticated-orcid":false,"given":"Kunlong","family":"Chen","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4112-3504","authenticated-orcid":false,"given":"Ziqi","family":"Liu","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2321-7259","authenticated-orcid":false,"given":"Zhiqiang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6033-6102","authenticated-orcid":false,"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","volume-title":"Large language models for mathematical reasoning: Progresses and challenges. arXiv preprint arXiv:2402.00157","author":"Ahn Janice","year":"2024","unstructured":"Janice Ahn, Rishu Verma, Renze Lou, Di Liu, Rui Zhang, and Wenpeng Yin. 2024. Large language models for mathematical reasoning: Progresses and challenges. arXiv preprint arXiv:2402.00157 (2024)."},{"key":"e_1_3_2_1_3_1","volume-title":"Stephen McAleer, Albert Q Jiang, Jia Deng, Stella Biderman, and Sean Welleck.","author":"Azerbayev Zhangir","year":"2023","unstructured":"Zhangir Azerbayev, Hailey Schoelkopf, Keiran Paster, Marco Dos Santos, Stephen McAleer, Albert Q Jiang, Jia Deng, Stella Biderman, and Sean Welleck. 2023. Llemma: An open language model for mathematics. arXiv preprint arXiv:2310.10631 (2023)."},{"key":"e_1_3_2_1_4_1","unstructured":"Karl Cobbe Vineet Kosaraju Mohammad Bavarian Mark Chen Heewoo Jun Lukasz Kaiser Matthias Plappert Jerry Tworek Jacob Hilton Reiichiro Nakano et al. 2021. Training verifiers to solve math word problems. arXiv preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_1_5_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_1_6_1","unstructured":"Aaron Grattafiori Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Alex Vaughan et al. 2024. The llama 3 herd of models. arXiv preprint arXiv:2407.21783 (2024)."},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.)","volume":"1","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. In Proceedings of the Neural Information Processing Systems Track on Datasets and Benchmarks, J. Vanschoren and S. Yeung (Eds.), Vol. 1."},{"key":"e_1_3_2_1_8_1","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra Singh Chaplot Diego de las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier L\u00e9lio Renard Lavaud Marie-Anne Lachaux Pierre Stock Teven Le Scao Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2023. Mistral 7B. arXiv:2310.06825 [cs.CL]"},{"key":"e_1_3_2_1_9_1","first-page":"3843","article-title":"Solving quantitative reasoning problems with language models","volume":"35","author":"Lewkowycz Aitor","year":"2022","unstructured":"Aitor Lewkowycz, Anders Andreassen, David Dohan, Ethan Dyer, Henryk Michalewski, Vinay Ramasesh, Ambrose Slone, Cem Anil, Imanol Schlag, Theo Gutman-Solo, et al., 2022. Solving quantitative reasoning problems with language models. Advances in Neural Information Processing Systems, Vol. 35 (2022), 3843-3857.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_10_1","volume-title":"Neuro-symbolic data generation for math reasoning (NIPS '24)","author":"Li Zenan","unstructured":"Zenan Li, Zhi Zhou, Yuan Yao, Yu-Feng Li, Chun Cao, Fan Yang, Xian Zhang, and Xiaoxing Ma. 2025. Neuro-symbolic data generation for math reasoning (NIPS '24). Curran Associates Inc., Red Hook, NY, USA, Article 740, 28 pages."},{"key":"e_1_3_2_1_11_1","volume-title":"A survey of deep learning for mathematical reasoning. arXiv preprint arXiv:2212.10535","author":"Lu Pan","year":"2022","unstructured":"Pan Lu, Liang Qiu, Wenhao Yu, Sean Welleck, and Kai-Wei Chang. 2022. A survey of deep learning for mathematical reasoning. arXiv preprint arXiv:2212.10535 (2022)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.151"},{"key":"e_1_3_2_1_13_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_1_14_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.168"},{"key":"e_1_3_2_1_15_1","volume-title":"Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300","author":"Shao Zhihong","year":"2024","unstructured":"Zhihong Shao, Peiyi Wang, Qihao Zhu, Runxin Xu, Junxiao Song, Xiao Bi, Haowei Zhang, Mingchuan Zhang, YK Li, Y Wu, et al., 2024. Deepseekmath: Pushing the limits of mathematical reasoning in open language models. arXiv preprint arXiv:2402.03300 (2024)."},{"key":"e_1_3_2_1_16_1","unstructured":"Ling Team Binwei Zeng Chao Huang Chao Zhang Changxin Tian Cong Chen Dingnan Jin Feng Yu Feng Zhu Feng Yuan et al. 2025. Every FLOP Counts: Scaling a 300B Mixture-of-Experts LING LLM without Premium GPUs. arXiv preprint arXiv:2503.05139 (2025)."},{"key":"e_1_3_2_1_17_1","volume-title":"Mathcoder: Seamless code integration in llms for enhanced mathematical reasoning. arXiv preprint arXiv:2310.03731","author":"Wang Ke","year":"2023","unstructured":"Ke Wang, Houxing Ren, Aojun Zhou, Zimu Lu, Sichun Luo, Weikang Shi, Renrui Zhang, Linqi Song, Mingjie Zhan, and Hongsheng Li. 2023. Mathcoder: Seamless code integration in llms for enhanced mathematical reasoning. arXiv preprint arXiv:2310.03731 (2023)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01820"},{"key":"e_1_3_2_1_19_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., 2022. 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_1_20_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. 2023. Metamath: Bootstrap your own mathematical questions for large language models. arXiv preprint arXiv:2309.12284 (2023)."},{"key":"e_1_3_2_1_21_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_1_22_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong et al. 2023. A survey of large language models. arXiv preprint arXiv:2303.18223 Vol. 1 2 (2023)."},{"key":"e_1_3_2_1_23_1","volume-title":"Jing Sha, Zhichao Sheng, Shijin Wang, and Ji-Rong Wen.","author":"Zhou Kun","year":"2024","unstructured":"Kun Zhou, Beichen Zhang, Jiapeng Wang, Zhipeng Chen, Wayne Xin Zhao, Jing Sha, Zhichao Sheng, Shijin Wang, and Ji-Rong Wen. 2024. JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models. In Advances in Neural Information Processing Systems, A. Globerson, L. Mackey, D. Belgrave, A. Fan, U. Paquet, J. Tomczak, and C. Zhang (Eds.), Vol. 37. Curran Associates, Inc., 1854-1889."}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3760944","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T02:07:31Z","timestamp":1765505251000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3760944"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":23,"alternative-id":["10.1145\/3746252.3760944","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3760944","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}