{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T13:40:30Z","timestamp":1773841230914,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,24]],"date-time":"2024-08-24T00:00:00Z","timestamp":1724457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,25]]},"DOI":"10.1145\/3637528.3671646","type":"proceedings-article","created":{"date-parts":[[2024,8,25]],"date-time":"2024-08-25T04:55:12Z","timestamp":1724561712000},"page":"5018-5027","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":40,"title":["Intelligent Agents with LLM-based Process Automation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0905-4396","authenticated-orcid":false,"given":"Yanchu","family":"Guan","sequence":"first","affiliation":[{"name":"Ant Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2942-0220","authenticated-orcid":false,"given":"Dong","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6075-1816","authenticated-orcid":false,"given":"Zhixuan","family":"Chu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5376-6761","authenticated-orcid":false,"given":"Shiyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6062-3459","authenticated-orcid":false,"given":"Feiyue","family":"Ni","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2163-7401","authenticated-orcid":false,"given":"Ruihua","family":"Song","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1891-5666","authenticated-orcid":false,"given":"Chenyi","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}]}],"member":"320","published-online":{"date-parts":[[2024,8,24]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49186-4_31"},{"key":"e_1_3_2_2_2_1","volume-title":"Baichuan 2: Open Large-scale Language Models. arXiv preprint arXiv:2309.10305","year":"2023","unstructured":"Baichuan. 2023. Baichuan 2: Open Large-scale Language Models. arXiv preprint arXiv:2309.10305 (2023). https:\/\/arxiv.org\/abs\/2309.10305"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Yejin Bang Samuel Cahyawijaya Nayeon Lee Wenliang Dai Dan Su Bryan Wilie Holy Lovenia Ziwei Ji Tiezheng Yu Willy Chung et al. 2023. A multitask multilingual multimodal evaluation of chatgpt on reasoning hallucination and interactivity. arXiv preprint arXiv:2302.04023 (2023).","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"e_1_3_2_2_4_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. Advances in neural information processing systems Vol. 33 (2020) 1877--1901."},{"key":"e_1_3_2_2_5_1","volume-title":"CHATBOT: Architecture, design, & development","author":"Cahn Jack","year":"2017","unstructured":"Jack Cahn. 2017. CHATBOT: Architecture, design, & development. University of Pennsylvania School of Engineering and Applied Science Department of Computer and Information Science (2017)."},{"key":"e_1_3_2_2_6_1","unstructured":"Zhixuan Chu Huaiyu Guo Xinyuan Zhou Yijia Wang Fei Yu Hong Chen Wanqing Xu Xin Lu Qing Cui Longfei Li Jun Zhou and Sheng Li. 2023. Data-Centric Financial Large Language Models. arxiv: 2310.17784 [cs.CL]"},{"key":"e_1_3_2_2_7_1","unstructured":"Zhixuan Chu Hongyan Hao Xin Ouyang Simeng Wang Yan Wang Yue Shen Jinjie Gu Qing Cui Longfei Li Siqiao Xue et al. 2023. Leveraging large language models for pre-trained recommender systems. arXiv preprint arXiv:2308.10837 (2023)."},{"key":"e_1_3_2_2_8_1","volume-title":"Llm-guided multi-view hypergraph learning for human-centric explainable recommendation. arXiv preprint arXiv:2401.08217","author":"Chu Zhixuan","year":"2024","unstructured":"Zhixuan Chu, Yan Wang, Qing Cui, Longfei Li, Wenqing Chen, Sheng Li, Zhan Qin, and Kui Ren. 2024. Llm-guided multi-view hypergraph learning for human-centric explainable recommendation. arXiv preprint arXiv:2401.08217 (2024)."},{"key":"e_1_3_2_2_9_1","volume-title":"A Causal Explainable Guardrails for Large Language Models. arXiv preprint arXiv:2405.04160","author":"Chu Zhixuan","year":"2024","unstructured":"Zhixuan Chu, Yan Wang, Longfei Li, Zhibo Wang, Zhan Qin, and Kui Ren. 2024. A Causal Explainable Guardrails for Large Language Models. arXiv preprint arXiv:2405.04160 (2024)."},{"key":"e_1_3_2_2_10_1","volume-title":"Professional Agents--Evolving Large Language Models into Autonomous Experts with Human-Level Competencies. arXiv preprint arXiv:2402.03628","author":"Chu Zhixuan","year":"2024","unstructured":"Zhixuan Chu, Yan Wang, Feng Zhu, Lu Yu, Longfei Li, and Jinjie Gu. 2024. Professional Agents--Evolving Large Language Models into Autonomous Experts with Human-Level Competencies. arXiv preprint arXiv:2402.03628 (2024)."},{"key":"e_1_3_2_2_11_1","volume-title":"2024 d. Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models. arXiv preprint arXiv:2405.04180","author":"Chu Zhixuan","year":"2024","unstructured":"Zhixuan Chu, Lei Zhang, Yichen Sun, Siqiao Xue, Zhibo Wang, Zhan Qin, and Kui Ren. 2024 d. Sora Detector: A Unified Hallucination Detection for Large Text-to-Video Models. arXiv preprint arXiv:2405.04180 (2024)."},{"key":"e_1_3_2_2_12_1","volume-title":"Mind2Web: Towards a Generalist Agent for the Web. arXiv preprint arXiv:2306.06070","author":"Deng Xiang","year":"2023","unstructured":"Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Samuel Stevens, Boshi Wang, Huan Sun, and Yu Su. 2023. Mind2Web: Towards a Generalist Agent for the Web. arXiv preprint arXiv:2306.06070 (2023)."},{"key":"e_1_3_2_2_13_1","volume-title":"Chain-of-verification reduces hallucination in large language models. arXiv preprint arXiv:2309.11495","author":"Dhuliawala Shehzaad","year":"2023","unstructured":"Shehzaad Dhuliawala, Mojtaba Komeili, Jing Xu, Roberta Raileanu, Xian Li, Asli Celikyilmaz, and Jason Weston. 2023. Chain-of-verification reduces hallucination in large language models. arXiv preprint arXiv:2309.11495 (2023)."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599572"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"e_1_3_2_2_16_1","volume-title":"Shixiang Shane Gu, and Izzeddin Gur","author":"Furuta Hiroki","year":"2023","unstructured":"Hiroki Furuta, Ofir Nachum, Kuang-Huei Lee, Yutaka Matsuo, Shixiang Shane Gu, and Izzeddin Gur. 2023. Multimodal Web Navigation with Instruction-Finetuned Foundation Models. arXiv preprint arXiv:2305.11854 (2023)."},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101167"},{"key":"e_1_3_2_2_18_1","volume-title":"Yolox: Exceeding yolo series in","author":"Ge Zheng","year":"2021","unstructured":"Zheng Ge, Songtao Liu, Feng Wang, Zeming Li, and Jian Sun. 2021. Yolox: Exceeding yolo series in 2021. arXiv preprint arXiv:2107.08430 (2021)."},{"key":"e_1_3_2_2_19_1","volume-title":"Zijuan Lin, Liyang Zhou, Chenyu Ran, et al.","author":"Hong Sirui","year":"2023","unstructured":"Sirui Hong, Xiawu Zheng, Jonathan Chen, Yuheng Cheng, Ceyao Zhang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, et al. 2023. Metagpt: Meta programming for multi-agent collaborative framework. arXiv preprint arXiv:2308.00352 (2023)."},{"key":"e_1_3_2_2_20_1","volume-title":"Time-llm: Time series forecasting by reprogramming large language models. arXiv preprint arXiv:2310.01728","author":"Jin Ming","year":"2023","unstructured":"Ming Jin, Shiyu Wang, Lintao Ma, Zhixuan Chu, James Y Zhang, Xiaoming Shi, Pin-Yu Chen, Yuxuan Liang, Yuan-Fang Li, Shirui Pan, et al. 2023. Time-llm: Time series forecasting by reprogramming large language models. arXiv preprint arXiv:2310.01728 (2023)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959134"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.5120\/ijca2017913083"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376209"},{"key":"e_1_3_2_2_24_1","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu Pengfei","year":"2023","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys, Vol. 55, 9 (2023), 1--35.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_2_25_1","volume-title":"Agentbench: Evaluating llms as agents. arXiv preprint arXiv:2308.03688","author":"Liu Xiao","year":"2023","unstructured":"Xiao Liu, Hao Yu, Hanchen Zhang, Yifan Xu, Xuanyu Lei, Hanyu Lai, Yu Gu, Hangliang Ding, Kaiwen Men, Kejuan Yang, et al. 2023. Agentbench: Evaluating llms as agents. arXiv preprint arXiv:2308.03688 (2023)."},{"key":"e_1_3_2_2_26_1","volume-title":"2023 USENIX Annual Technical Conference (USENIX ATC 23)","author":"Ma Junming","year":"2023","unstructured":"Junming Ma, Yancheng Zheng, Jun Feng, Derun Zhao, Haoqi Wu, Wenjing Fang, Jin Tan, Chaofan Yu, Benyu Zhang, and Lei Wang. 2023. $$SecretFlow-SPU$$: A Performant and $$User-Friendly$$ Framework for $$Privacy-Preserving$$ Machine Learning. In 2023 USENIX Annual Technical Conference (USENIX ATC 23). 17--33."},{"key":"e_1_3_2_2_27_1","unstructured":"OpenAI. 2022. Introducing chatgpt. (2022)."},{"key":"e_1_3_2_2_29_1","volume-title":"Intelligible description language contract (IDLC)--A novel smart contract model. Information Systems Frontiers","author":"Qin Peng","year":"2021","unstructured":"Peng Qin, Weiming Tan, Jingzhi Guo, and Bingqing Shen. 2021. Intelligible description language contract (IDLC)--A novel smart contract model. Information Systems Frontiers (2021), 1--18."},{"key":"e_1_3_2_2_30_1","volume-title":"Android in the wild: A large-scale dataset for android device control. arXiv preprint arXiv:2307.10088","author":"Rawles Christopher","year":"2023","unstructured":"Christopher Rawles, Alice Li, Daniel Rodriguez, Oriana Riva, and Timothy Lillicrap. 2023. Android in the wild: A large-scale dataset for android device control. arXiv preprint arXiv:2307.10088 (2023)."},{"key":"e_1_3_2_2_31_1","volume-title":"Flowris: Managing Data Analysis Workflows for Conversational Agent. In International Conference on Database Systems for Advanced Applications. Springer, 724--728","author":"Sun Jiajia","year":"2023","unstructured":"Jiajia Sun, Juan Wang, Yueguo Chen, and Xiongpai Qin. 2023. Flowris: Managing Data Analysis Workflows for Conversational Agent. In International Conference on Database Systems for Advanced Applications. Springer, 724--728."},{"key":"e_1_3_2_2_32_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_2_33_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29887"},{"key":"e_1_3_2_2_35_1","unstructured":"Yan Wang Zhixuan Chu Xin Ouyang Simeng Wang Hongyan Hao Yue Shen Jinjie Gu Siqiao Xue James Y Zhang Qing Cui et al. 2023. Enhancing recommender systems with large language model reasoning graphs. arXiv preprint arXiv:2308.10835 (2023)."},{"key":"e_1_3_2_2_36_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","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.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_37_1","volume-title":"A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382","author":"White Jules","year":"2023","unstructured":"Jules White, Quchen Fu, Sam Hays, Michael Sandborn, Carlos Olea, Henry Gilbert, Ashraf Elnashar, Jesse Spencer-Smith, and Douglas C Schmidt. 2023. A prompt pattern catalog to enhance prompt engineering with chatgpt. arXiv preprint arXiv:2302.11382 (2023)."},{"key":"e_1_3_2_2_38_1","volume-title":"Prompt-augmented temporal point process for streaming event sequence. arXiv preprint arXiv:2310.04993","author":"Xue Siqiao","year":"2023","unstructured":"Siqiao Xue, Yan Wang, Zhixuan Chu, Xiaoming Shi, Caigao Jiang, Hongyan Hao, Gangwei Jiang, Xiaoyun Feng, James Y Zhang, and Jun Zhou. 2023. Prompt-augmented temporal point process for streaming event sequence. arXiv preprint arXiv:2310.04993 (2023)."},{"key":"e_1_3_2_2_39_1","volume-title":"Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Thomas L Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. arXiv preprint arXiv:2305.10601 (2023)."},{"key":"e_1_3_2_2_40_1","unstructured":"Aohan Zeng Xiao Liu Zhengxiao Du Zihan Wang Hanyu Lai Ming Ding Zhuoyi Yang Yifan Xu Wendi Zheng Xiao Xia et al. 2022. Glm-130b: An open bilingual pre-trained model. arXiv preprint arXiv:2210.02414 (2022)."},{"key":"e_1_3_2_2_41_1","volume-title":"You only look at screens: Multimodal chain-of-action agents. arXiv preprint arXiv:2309.11436","author":"Zhan Zhuosheng","year":"2023","unstructured":"Zhuosheng Zhan and Aston Zhang. 2023. You only look at screens: Multimodal chain-of-action agents. arXiv preprint arXiv:2309.11436 (2023)."},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445186"},{"key":"e_1_3_2_2_43_1","unstructured":"Yue Zhang Yafu Li Leyang Cui Deng Cai Lemao Liu Tingchen Fu Xinting Huang Enbo Zhao Yu Zhang Yulong Chen et al. 2023. Siren's Song in the AI Ocean: A Survey on Hallucination in Large Language Models. arXiv preprint arXiv:2309.01219 (2023)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1692-3"},{"key":"e_1_3_2_2_45_1","volume-title":"Object detection in 20 years: A survey. Proc","author":"Zou Zhengxia","year":"2023","unstructured":"Zhengxia Zou, Keyan Chen, Zhenwei Shi, Yuhong Guo, and Jieping Ye. 2023. Object detection in 20 years: A survey. Proc. IEEE (2023)."}],"event":{"name":"KDD '24: The 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Barcelona Spain","acronym":"KDD '24","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 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671646","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3637528.3671646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:06:00Z","timestamp":1750291560000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3637528.3671646"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,24]]},"references-count":44,"alternative-id":["10.1145\/3637528.3671646","10.1145\/3637528"],"URL":"https:\/\/doi.org\/10.1145\/3637528.3671646","relation":{},"subject":[],"published":{"date-parts":[[2024,8,24]]},"assertion":[{"value":"2024-08-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}