{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T22:38:11Z","timestamp":1792795091059,"version":"4.5.0"},"publisher-location":"New York, NY, USA","reference-count":36,"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"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62272050"],"award-info":[{"award-number":["62272050"]}]},{"name":"Zhuhai Science-Tech Innovation Bureau","award":["2320004002772"],"award-info":[{"award-number":["2320004002772"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817460","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:47Z","timestamp":1786036547000},"page":"9973-9984","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["BacktestBench: Benchmarking Large Language Models for Automated Quantitative Strategy Backtesting"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-0395-8572","authenticated-orcid":false,"given":"Zhensheng","family":"Wang","sequence":"first","affiliation":[{"name":"Beijing Normal University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8493-4449","authenticated-orcid":false,"given":"Wenmian","family":"Yang","sequence":"additional","affiliation":[{"name":"Beijing Normal University, Zhuhai, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-7047-5689","authenticated-orcid":false,"given":"Qingtai","family":"Wu","sequence":"additional","affiliation":[{"name":"Beijing Normal University, Zhuhai, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8238-0295","authenticated-orcid":false,"given":"Lequan","family":"Ma","sequence":"additional","affiliation":[{"name":"Beijing Normal University, Zhuhai, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0505-8271","authenticated-orcid":false,"given":"Yiquan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Elmleaf Ltd., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1000-3937","authenticated-orcid":false,"given":"Weijia","family":"Jia","sequence":"additional","affiliation":[{"name":"Beijing Normal University, Zhuhai, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Yifan Bai Yiping Bao Guanduo Chen et al. 2025. Kimi K2: Open Agentic Intelligence. CoRR abs\/2507.20534 (2025). arXiv:2507.20534 doi:10.48550\/ARXIV.2507.20534","DOI":"10.48550\/ARXIV.2507.20534"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"Aili Chen Aonian Li Bangwei Gong et al. 2025. MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention. CoRR abs\/2506.13585 (2025). arXiv:2506.13585 doi:10.48550\/ARXIV.2506.13585","DOI":"10.48550\/ARXIV.2506.13585"},{"key":"e_1_3_2_1_3_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun et al. 2021. Evaluating Large Language Models Trained on Code. CoRR abs\/2107.03374 (2021). arXiv:2107.03374 https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2510.02209"},{"key":"e_1_3_2_1_5_1","volume-title":"Advances in financial machine learning","author":"De Prado Marcos Lopez","unstructured":"Marcos Lopez De Prado. 2018. Advances in financial machine learning. John Wiley & Sons."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2512.02556"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671629"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbankfin.2006.09.015"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.14778\/3748191.3748211"},{"key":"e_1_3_2_1_10_1","unstructured":"Gemma Team Aishwarya Kamath Johan Ferret Shreya Pathak et al. 2025. Gemma 3 Technical Report. arXiv:2503.19786 [cs.CL] https:\/\/arxiv.org\/abs\/2503.19786"},{"key":"e_1_3_2_1_11_1","volume-title":"Yunfei Feng, Yitong Leng, Junfan Zhu, Xiaoyou Chen, Xi Yang, and Richeng Xuan.","author":"Kang Zhaolu","year":"2026","unstructured":"Zhaolu Kang, Junhao Gong, Wenqing Hu, Shuo Yin, Kehan Jiang, Zhicheng Fang, Yingjie He, Chunlei Meng, Rong Fu, Dongyang Chen, Leqi Zheng, Eric Hanchen Jiang, Yunfei Feng, Yitong Leng, Junfan Zhu, Xiaoyou Chen, Xi Yang, and Richeng Xuan. 2026. QuantEval: A Benchmark for Financial Quantitative Tasks in Large Language Models. arXiv:2601.08689 [cs.CL] https:\/\/arxiv.org\/abs\/2601.08689"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2409.06289"},{"key":"e_1_3_2_1_13_1","volume-title":"The Thirteenth International Conference on Learning Representations, ICLR 2025","author":"Lei Fangyu","year":"2025","unstructured":"Fangyu Lei, Jixuan Chen, Yuxiao Ye, Ruisheng Cao, Dongchan Shin, Hongjin Su, Zhaoqing Suo, Hongcheng Gao, Wenjing Hu, Pengcheng Yin, Victor Zhong, Caiming Xiong, Ruoxi Sun, Qian Liu, Sida Wang, and Tao Yu. 2025. Spider 2.0: Evaluating Language Models on Real-World Enterprise Text-to-SQL Workflows. In The Thirteenth International Conference on Learning Representations, ICLR 2025, Singapore, April 24-28, 2025. OpenReview.net. https:\/\/openreview.net\/forum?id=XmProj9cPs"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1835"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0134"},{"key":"e_1_3_2_1_16_1","volume-title":"WizardCoder: Empowering Code Large Language Models with Evol-Instruct. In The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Luo Ziyang","year":"2024","unstructured":"Ziyang Luo, Can Xu, Pu Zhao, Qingfeng Sun, Xiubo Geng, Wenxiang Hu, Chongyang Tao, Jing Ma, Qingwei Lin, and Daxin Jiang. 2024. WizardCoder: Empowering Code Large Language Models with Evol-Instruct. In The Twelfth International Conference on Learning Representations, ICLR 2024, Vienna, Austria, May 7-11, 2024. OpenReview.net. https:\/\/openreview.net\/forum?id=UnUwSIgK5W"},{"key":"e_1_3_2_1_17_1","first-page":"99","article-title":"Maximum drawdown","volume":"17","author":"Magdon-Ismail Malik","year":"2004","unstructured":"Malik Magdon-Ismail and Amir F Atiya. 2004. Maximum drawdown. Risk Magazine 17, 10 (2004), 99-102.","journal-title":"Risk Magazine"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2508.10925"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1002\/9781119196969"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","unstructured":"Baptiste Rozi\u00e8re Jonas Gehring Fabian Gloeckle Sten Sootla Itai Gat Xiaoqing Ellen Tan Yossi Adi Jingyu Liu Tal Remez J\u00e9r\u00e9my Rapin Artyom Kozhevnikov Ivan Evtimov Joanna Bitton Manish Bhatt Cristian Canton-Ferrer Aaron Grattafiori Wenhan Xiong Alexandre D\u00e9fossez Jade Copet Faisal Azhar Hugo Touvron Louis Martin Nicolas Usunier Thomas Scialom and Gabriel Synnaeve. 2023. Code Llama: Open Foundation Models for Code. CoRR abs\/2308.12950 (2023). arXiv:2308.12950 doi:10.48550\/ARXIV.2308.12950","DOI":"10.48550\/ARXIV.2308.12950"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2997"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1515\/9781400829408-022"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2512.12264"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3226595.3226639"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2576"},{"key":"e_1_3_2_1_27_1","volume-title":"The Philosophy of Artificial Intelligence, Margaret A","author":"Turing Alan M.","unstructured":"Alan M. Turing. 1990. Computing Machinery and Intelligence. In The Philosophy of Artificial Intelligence, Margaret A. Boden (Ed.). Oxford University Press, 40-66."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2402.03755"},{"key":"e_1_3_2_1_29_1","unstructured":"LLM-Core Xiaomi. 2026. MiMo-V2-Flash Technical Report. arXiv:2601.02780 [cs.CL] https:\/\/arxiv.org\/abs\/2601.02780"},{"key":"e_1_3_2_1_30_1","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Xie Qianqian","year":"2023","unstructured":"Qianqian Xie, Weiguang Han, Xiao Zhang, Yanzhao Lai, Min Peng, Alejandro Lopez-Lira, and Jimin Huang. 2023. PIXIU: a large language model, instruction data and evaluation benchmark for finance. In Proceedings of the 37th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS '23). Curran Associates Inc., Red Hook, NY, USA, Article 1454, 16 pages."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","unstructured":"An Yang Anfeng Li Baosong Yang et al. 2025. Qwen3 Technical Report. CoRR abs\/2505.09388 (2025). arXiv:2505.09388 doi:10.48550\/ARXIV.2505.09388","DOI":"10.48550\/ARXIV.2505.09388"},{"key":"e_1_3_2_1_32_1","volume-title":"ReAct: Synergizing Reasoning and Acting in Language Models. In The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R. Narasimhan, and Yuan Cao. 2023. ReAct: Synergizing Reasoning and Acting in Language Models. In The Eleventh International Conference on Learning Representations, ICLR 2023, Kigali, Rwanda, May 1-5, 2023. OpenReview.net. https:\/\/openreview.net\/forum?id=WE_vluYUL-X"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599831"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","unstructured":"Tao Yu Rui Zhang Kai Yang Michihiro Yasunaga Dongxu Wang Zifan Li James Ma Irene Li Qingning Yao Shanelle Roman Zilin Zhang and Dragomir Radev. 2018. Spider: A Large-Scale Human-Labeled Dataset for Complex and Cross-Domain Semantic Parsing and Text-to-SQL Task. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing Ellen Riloff David Chiang Julia Hockenmaier and Jun'ichi Tsujii (Eds.). Association for Computational Linguistics Brussels Belgium 3911-3921. doi:10.18653\/v1\/D18-1425","DOI":"10.18653\/v1\/D18-1425"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2025.3593370"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","unstructured":"Aohan Zeng Xin Lv Qinkai Zheng et al. 2025. GLM-4.5: Agentic Reasoning and Coding (ARC) Foundation Models. CoRR abs\/2508.06471 (2025). arXiv:2508.06471 doi:10.48550\/ARXIV.2508.06471","DOI":"10.48550\/ARXIV.2508.06471"}],"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":"2026-08-07T01:27:46Z","timestamp":1786066066000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817460"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":36,"alternative-id":["10.1145\/3770855.3817460","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817460","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"}}]}}