{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:33:56Z","timestamp":1773246836406,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","funder":[{"name":"EPSRC","award":["EP\/S026347\/1, EP\/N510129\/1"],"award-info":[{"award-number":["EP\/S026347\/1, EP\/N510129\/1"]}]},{"name":"UCL Centre for Digital Innovation, powered by Amazon Web Services","award":[""],"award-info":[{"award-number":[""]}]},{"name":"Ministry of Education, Singapore","award":["T1 251RES2517"],"award-info":[{"award-number":["T1 251RES2517"]}]},{"name":"UKRI","award":["EP\/V056883\/1, APP43592"],"award-info":[{"award-number":["EP\/V056883\/1, APP43592"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,15]]},"DOI":"10.1145\/3768292.3771251","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:24:26Z","timestamp":1763105066000},"page":"924-932","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Structured Agentic Workflows for Financial Time-Series Modelling with LLMs and Reflective Feedback"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-1564-4937","authenticated-orcid":false,"given":"Yihao","family":"Ang","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9672-0747","authenticated-orcid":false,"given":"Yifan","family":"Bao","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9446-8118","authenticated-orcid":false,"given":"Lei","family":"Jiang","sequence":"additional","affiliation":[{"name":"University College London, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8468-9218","authenticated-orcid":false,"given":"Jiajie","family":"Tao","sequence":"additional","affiliation":[{"name":"University College London, London, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7300-6196","authenticated-orcid":false,"given":"Anthony K. H.","family":"Tung","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4889-4587","authenticated-orcid":false,"given":"Lukasz","family":"Szpurch","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5485-4376","authenticated-orcid":false,"given":"Hao","family":"Ni","sequence":"additional","affiliation":[{"name":"University College London, London, United Kingdom"}]}],"member":"320","published-online":{"date-parts":[[2025,11,14]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Yihao Ang Yifan Bao Qiang Huang Anthony\u00a0KH Tung and Zhiyong Huang. 2024. Tsgassist: An interactive assistant harnessing llms and rag for time series generation recommendations and benchmarking. Proceedings of the VLDB Endowment 17 12 (2024) 4309\u20134312.","DOI":"10.14778\/3685800.3685862"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Yihao Ang Qiang Huang Yifan Bao Anthony\u00a0KH Tung and Zhiyong Huang. 2023. TSGBench: Time Series Generation Benchmark. Proc. VLDB Endow. 17 3 (2023) 305\u2013318.","DOI":"10.14778\/3632093.3632097"},{"key":"e_1_3_3_1_5_2","unstructured":"Yihao Ang Qiang Wang Qiang Huang Yifan Bao Xinyu Xi Anthony\u00a0KH Tung Chen Jin and Zhiyong Huang. 2025. CTBench: Cryptocurrency Time Series Generation Benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2508.02758 (2025)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.342"},{"key":"e_1_3_3_1_7_2","unstructured":"Abhyuday Desai Cynthia Freeman Zuhui Wang and Ian Beaver. 2021. Timevae: A variational auto-encoder for multivariate time series generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2111.08095 (2021)."},{"key":"e_1_3_3_1_8_2","unstructured":"David Eriksson and et al.2023. AutoGluon-TimeSeries: Robust AutoML for Time Series Forecasting. https:\/\/github.com\/autogluon\/autogluon. Accessed: 2025-07-30."},{"key":"e_1_3_3_1_9_2","unstructured":"Crist\u00f3bal Esteban Stephanie\u00a0L Hyland and Gunnar R\u00e4tsch. 2017. Real-valued (medical) time series generation with recurrent conditional gans. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1706.02633 (2017)."},{"key":"e_1_3_3_1_10_2","volume-title":"NeurIPS","author":"Feurer Matthias","year":"2015","unstructured":"Matthias Feurer, Aaron Klein, Katharina Eggensperger, Jost Springenberg, Manuel Blum, and Frank Hutter. 2015. Efficient and robust automated machine learning. In NeurIPS , Vol.\u00a028."},{"key":"e_1_3_3_1_11_2","unstructured":"Siyuan Guo Cheng Deng Ying Wen Hechang Chen Yi Chang and Jun Wang. 2024. DS-Agent: Automated Data Science by Empowering Large Language Models with Case-Based Reasoning. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.17453 (2024)."},{"key":"e_1_3_3_1_12_2","first-page":"6840","volume-title":"NeurIPS","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. In NeurIPS. 6840\u20136851."},{"key":"e_1_3_3_1_13_2","volume-title":"arXiv:https:\/\/arXiv.org\/abs\/2502.18834","author":"Hu Y.","year":"2025","unstructured":"Y. Hu et\u00a0al. 2025. FinTSB: A Comprehensive Benchmark for Financial Time Series Forecasting. In arXiv:https:\/\/arXiv.org\/abs\/2502.18834."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3209978.3210006"},{"key":"e_1_3_3_1_15_2","unstructured":"Erin LeDell and Sebastien Poirier. 2020. H2O AutoML: Scalable Automatic Machine Learning. 7th ICML Workshop on Automated Machine Learning (AutoML) (2020)."},{"key":"e_1_3_3_1_16_2","first-page":"39755","volume-title":"NeurIPS","author":"Lou Hang","year":"2023","unstructured":"Hang Lou, Siran Li, and Hao Ni. 2023. PCF-GAN: generating sequential data via the characteristic function of measures on the path space. In NeurIPS. 39755\u201339781."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490354.3494393"},{"key":"e_1_3_3_1_18_2","unstructured":"Hao Ni Lukasz Szpruch and Jiajie Tao. 2023. Regime-switching Financial Time-Series Generation. https:\/\/github.com\/tjj0502\/hackathon_starting_kit. ICAIF 2023 Hackathon."},{"key":"e_1_3_3_1_19_2","unstructured":"Hao Ni Lukasz Szpruch Jiajie Tao and Yang Long. 2024. Crypto Market Simulation for Risk Estimation. https:\/\/hackathon.deepintomlf.ai\/competitions\/40. Antalpha ICAIF 2024 Hackathon."},{"key":"e_1_3_3_1_20_2","unstructured":"Hao Ni and Jiajie Tao. 2023. Market Scenario Generator Hackathon: From Stability to Storms. https:\/\/github.com\/DeepIntoStreams\/Market_Scenario_Generator_Hackathon_starting_kit. ICAIF 2023 Hackathon."},{"key":"e_1_3_3_1_21_2","volume-title":"ICLR","author":"Nie Yuqi","year":"2023","unstructured":"Yuqi Nie, Nam\u00a0H Nguyen, Phanwadee Sinthong, and Jayant Kalagnanam. 2023. A Time Series is Worth 64 Words: Long-term Forecasting with Transformers. In ICLR."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Rasmus\u00a0V Rasmussen and Michael\u00a0A Trick. 2008. Round robin scheduling\u2013a survey. European Journal of Operational Research 188 3 (2008) 617\u2013636.","DOI":"10.1016\/j.ejor.2007.05.046"},{"key":"e_1_3_3_1_23_2","unstructured":"Toran\u00a0Bruce Richards. 2023. AutoGPT: An Autonomous GPT-4 Experiment. https:\/\/github.com\/Torantulino\/Auto-GPT."},{"key":"e_1_3_3_1_24_2","first-page":"8634","volume-title":"NeurIPS","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. In NeurIPS , Vol.\u00a036. 8634\u20138652."},{"key":"e_1_3_3_1_25_2","unstructured":"Amanpreet Singh and et al.2023. Large Language Models Orchestrating Structured Reasoning Achieve Kaggle Grandmaster Level. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.05068 (2023)."},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487629"},{"key":"e_1_3_3_1_27_2","unstructured":"Guanzhi Wang Yuqi Xie Yunfan Jiang Ajay Mandlekar Chaowei Xiao Yuke Zhu Linxi Fan and Anima Anandkumar. [n.d.]. Voyager: An Open-Ended Embodied Agent with Large Language Models. TMLR ([n. d.])."},{"key":"e_1_3_3_1_28_2","volume-title":"ICLR","author":"Wang Shiyu","year":"2024","unstructured":"Shiyu Wang, Haixu Wu, Xiaoming Shi, Tengge Hu, Huakun Luo, Lintao Ma, James\u00a0Y Zhang, and JUN ZHOU. 2024. TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting. In ICLR."},{"key":"e_1_3_3_1_29_2","unstructured":"Yanlong Wang Jian Xu Tiantian Gao Hongkang Zhang Shao-Lun Huang Danny\u00a0Dongning Sun and Xiao-Ping Zhang. 2025. FinTSBridge: A New Evaluation Suite for Real-world Financial Prediction with Advanced Time Series Models. arXiv:https:\/\/arXiv.org\/abs\/2503.06928 (2025)."},{"key":"e_1_3_3_1_30_2","volume-title":"ICLR","author":"Wu Haixu","year":"2023","unstructured":"Haixu Wu, Tengge Hu, Yong Liu, Hang Zhou, Jianmin Wang, and Mingsheng Long. 2023. TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis. In ICLR."},{"key":"e_1_3_3_1_31_2","first-page":"22419","volume-title":"NeurIPS","author":"Wu Haixu","year":"2021","unstructured":"Haixu Wu, Jiehui Xu, Jianmin Wang, and Mingsheng Long. 2021. Autoformer: Decomposition transformers with auto-correlation for long-term series forecasting. In NeurIPS , Vol.\u00a034. 22419\u201322430."},{"key":"e_1_3_3_1_32_2","unstructured":"Shinn Yao Jiong Zhao Dian Yu and et al.2022. ReAct: Synergizing Reasoning and Acting in Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.03629 (2022)."},{"key":"e_1_3_3_1_33_2","first-page":"5509","volume-title":"NeurIPS","author":"Yoon Jinsung","year":"2019","unstructured":"Jinsung Yoon, Daniel Jarrett, and Mihaela van\u00a0der Schaar. 2019. Time-series Generative Adversarial Networks. In NeurIPS. 5509\u20135519."},{"key":"e_1_3_3_1_34_2","first-page":"5509","volume-title":"NeurIPS","author":"Yoon Jinsung","year":"2019","unstructured":"Jinsung Yoon, Daniel Jarrett, and Mihaela van\u00a0der Schaar. 2019. Time-series Generative Adversarial Networks. In NeurIPS. 5509\u20135519."},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26317"}],"event":{"name":"ICAIF '25: 6th ACM International Conference on AI in Finance","location":"Singapore Singapore","acronym":"ICAIF '25"},"container-title":["Proceedings of the 6th ACM International Conference on AI in Finance"],"original-title":[],"deposited":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T07:31:23Z","timestamp":1763105483000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3768292.3771251"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,14]]},"references-count":34,"alternative-id":["10.1145\/3768292.3771251","10.1145\/3768292"],"URL":"https:\/\/doi.org\/10.1145\/3768292.3771251","relation":{},"subject":[],"published":{"date-parts":[[2025,11,14]]},"assertion":[{"value":"2025-11-14","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}