{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:21:07Z","timestamp":1780392067557,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","funder":[{"name":"National Key R\\&D Program of China","award":["No.2023YFF0725004"],"award-info":[{"award-number":["No.2023YFF0725004"]}]},{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No.92370204"],"award-info":[{"award-number":["No.92370204"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou Basic and Applied Basic Research Program","award":["2024A04J3279"],"award-info":[{"award-number":["2024A04J3279"]}]},{"name":"Education Bureau of Guangzhou Municipality"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,3]]},"DOI":"10.1145\/3711896.3737208","type":"proceedings-article","created":{"date-parts":[[2025,8,3]],"date-time":"2025-08-03T21:04:26Z","timestamp":1754255066000},"page":"4728-4739","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["DiMA: An LLM-Powered Ride-Hailing Assistant at DiDi"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8691-4999","authenticated-orcid":false,"given":"Yansong","family":"Ning","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4293-332X","authenticated-orcid":false,"given":"Shuowei","family":"Cai","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), GuangZhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0263-429X","authenticated-orcid":false,"given":"Wei","family":"Li","sequence":"additional","affiliation":[{"name":"Didichuxing Co. Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6083-1234","authenticated-orcid":false,"given":"Jun","family":"Fang","sequence":"additional","affiliation":[{"name":"Didichuxing Co. Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4687-5212","authenticated-orcid":false,"given":"Naiqiang","family":"Tan","sequence":"additional","affiliation":[{"name":"Didichuxing Co. Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3381-2526","authenticated-orcid":false,"given":"Hua","family":"Chai","sequence":"additional","affiliation":[{"name":"Didichuxing Co. Ltd, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4271-1567","authenticated-orcid":false,"given":"Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,8,3]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Apple. [n.d.]. Siri - Human Interface Guidelines. https:\/\/developer.apple.com\/design\/human-interface-guidelines\/siri\/. Accessed: 2024-09-27."},{"key":"e_1_3_2_2_2_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609(2023)."},{"key":"e_1_3_2_2_3_1","unstructured":"Hritik Bansal Arian Hosseini Rishabh Agarwal Vinh Q Tran and Mehran Kazemi. 2024. Smaller weaker yet better: Training llm reasoners via compute-optimal sampling. arXiv preprint arXiv:2408.16737(2024)."},{"key":"e_1_3_2_2_4_1","volume-title":"Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing. 225-232","author":"Bohus Dan","year":"2005","unstructured":"Dan Bohus and Alexander Rudnicky. 2005. Error handling in the RavenClaw dialog management architecture. In Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing. 225-232."},{"key":"e_1_3_2_2_5_1","volume-title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads. arXiv preprint arXiv: 2401.10774(2024).","author":"Cai Tianle","year":"2024","unstructured":"Tianle Cai, Yuhong Li, Zhengyang Geng, Hongwu Peng, Jason D. Lee, Deming Chen, and Tri Dao. 2024. Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads. arXiv preprint arXiv: 2401.10774(2024)."},{"key":"e_1_3_2_2_6_1","unstructured":"Zixiang Chen Yihe Deng Huizhuo Yuan Kaixuan Ji and Quanquan Gu. 2024. Self-play fine-tuning converts weak language models to strong language models. arXiv preprint arXiv:2401.01335(2024)."},{"key":"e_1_3_2_2_7_1","volume-title":"Instructtods: Large language models for end-to-end task-oriented dialogue systems. arXiv preprint arXiv:2310.08885(2023).","author":"Chung Willy","year":"2023","unstructured":"Willy Chung, Samuel Cahyawijaya, Bryan Wilie, Holy Lovenia, and Pascale Fung. 2023. Instructtods: Large language models for end-to-end task-oriented dialogue systems. arXiv preprint arXiv:2310.08885(2023)."},{"key":"e_1_3_2_2_8_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Deng Xiang","year":"2024","unstructured":"Xiang Deng, Yu Gu, Boyuan Zheng, Shijie Chen, Sam Stevens, Boshi Wang, Huan Sun, and Yu Su. 2024. Mind2web: Towards a generalist agent for the web. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599572"},{"key":"e_1_3_2_2_10_1","unstructured":"Albert Qiaochu Jiang et al. 2023. Mistral 7B. ArXiv Vol. abs\/2310.06825 (2023). https:\/\/api.semanticscholar.org\/CorpusID:263830494"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1287\/msom.2020.0880"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671622"},{"key":"e_1_3_2_2_13_1","unstructured":"Yunfan Gao Yun Xiong Xinyu Gao Kangxiang Jia Jinliu Pan Yuxi Bi Yi Dai Jiawei Sun and Haofen Wang. 2023. Retrieval-augmented generation for large language models: A survey. arXiv preprint arXiv:2312.10997(2023)."},{"key":"e_1_3_2_2_14_1","unstructured":"Yanchu Guan Dong Wang Zhixuan Chu Shiyu Wang Feiyue Ni Ruihua Song Longfei Li Jinjie Gu and Chenyi Zhuang. 2023. Intelligent virtual assistants with llm-based process automation. arXiv preprint arXiv:2312.06677(2023)."},{"key":"e_1_3_2_2_15_1","volume-title":"Mustafa Safdari, Yutaka Matsuo, Douglas Eck, and Aleksandra Faust.","author":"Gur Izzeddin","year":"2023","unstructured":"Izzeddin Gur, Hiroki Furuta, Austin Huang, Mustafa Safdari, Yutaka Matsuo, Douglas Eck, and Aleksandra Faust. 2023. A real-world webagent with planning, long context understanding, and program synthesis. arXiv preprint arXiv:2307.12856(2023)."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.14778\/3641204.3641217"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21320"},{"key":"e_1_3_2_2_18_1","first-page":"20179","article-title":"A simple language model for task-oriented dialogue","volume":"33","author":"Hosseini-Asl Ehsan","year":"2020","unstructured":"Ehsan Hosseini-Asl, Bryan McCann, Chien-Sheng Wu, Semih Yavuz, and Richard Socher. 2020. A simple language model for task-oriented dialogue. Advances in Neural Information Processing Systems, Vol. 33 (2020), 20179-20191.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_19_1","volume-title":"Usability Study on the User Interface Design of Ride-hailing Applications. In International Conference on Human-Computer Interaction. Springer, 208-216","author":"Hsu Yi-Hung","year":"2023","unstructured":"Yi-Hung Hsu and Chien-Hsiung Chen. 2023. Usability Study on the User Interface Design of Ride-hailing Applications. In International Conference on Human-Computer Interaction. Springer, 208-216."},{"key":"e_1_3_2_2_20_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685(2021).","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685(2021)."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"crossref","unstructured":"Vojt\u011bch Hude\u010dek and Ond\u0159ej Du\u0161ek. 2023. Are LLMs all you need for task-oriented dialogue? arXiv preprint arXiv:2304.06556(2023).","DOI":"10.18653\/v1\/2023.sigdial-1.21"},{"key":"e_1_3_2_2_22_1","volume-title":"Shuntian Yao, Yuxuan Chen, Pengbo Shen, Hao Yu, Hanchen Zhang, Xiaohan Zhang, Yuxiao Dong, et al.","author":"Lai Hanyu","year":"2024","unstructured":"Hanyu Lai, Xiao Liu, Iat Long Iong, Shuntian Yao, Yuxuan Chen, Pengbo Shen, Hao Yu, Hanchen Zhang, Xiaohan Zhang, Yuxiao Dong, et al., 2024. AutoWebGLM: Bootstrap And Reinforce A Large Language Model-based Web Navigating Agent. arXiv preprint arXiv:2404.03648(2024)."},{"key":"e_1_3_2_2_23_1","volume-title":"Mike Ross, Patrick Huber, Seungwhan Moon, Zhaojiang Lin, Xin Luna Dong, Adithya Sagar, Xifeng Yan, and Paul A Crook.","author":"Li Zekun","year":"2024","unstructured":"Zekun Li, Zhiyu Zoey Chen, Mike Ross, Patrick Huber, Seungwhan Moon, Zhaojiang Lin, Xin Luna Dong, Adithya Sagar, Xifeng Yan, and Paul A Crook. 2024. Large Language Models as Zero-shot Dialogue State Tracker through Function Calling. arXiv preprint arXiv:2402.10466(2024)."},{"key":"e_1_3_2_2_24_1","first-page":"87","article-title":"AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration","volume":"6","author":"Lin Ji","year":"2024","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration. Proceedings of Machine Learning and Systems, Vol. 6 (2024), 87-100.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599925"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.commtr.2022.100075"},{"key":"e_1_3_2_2_27_1","volume-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1. 985-996","author":"Lyu Tengfei","year":"2024","unstructured":"Tengfei Lyu, Weijia Zhang, Jinliang Deng, and Hao Liu. 2024. AutoSTF: Decoupled Neural Architecture Search for Cost-Effective Automated Spatio-Temporal Forecasting. In Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1. 985-996."},{"key":"e_1_3_2_2_28_1","unstructured":"OpenAI. 2023. Introducing ChatGPT. https:\/\/openai.com\/blog\/chatgpt. Accessed on 1 December 2023."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241581"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Libo Qin Wenbo Pan Qiguang Chen Lizi Liao Zhou Yu Yue Zhang Wanxiang Che and Min Li. 2023. End-to-end task-oriented dialogue: A survey of tasks methods and future directions. arXiv preprint arXiv:2311.09008(2023).","DOI":"10.18653\/v1\/2023.emnlp-main.363"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3409120.3410639"},{"key":"e_1_3_2_2_32_1","first-page":"391","article-title":"An overview of end-to-end language understanding and dialog management for personal digital assistants. In 2016 ieee spoken language technology workshop (slt)","author":"Sarikaya Ruhi","year":"2016","unstructured":"Ruhi Sarikaya, Paul A Crook, Alex Marin, Minwoo Jeong, Jean-Philippe Robichaud, Asli Celikyilmaz, Young-Bum Kim, Alexandre Rochette, Omar Zia Khan, Xiaohu Liu, et al., 2016. An overview of end-to-end language understanding and dialog management for personal digital assistants. In 2016 ieee spoken language technology workshop (slt). IEEE, 391-397.","journal-title":"IEEE"},{"key":"e_1_3_2_2_33_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_34_1","volume-title":"Timo: Towards Better Temporal Reasoning for Language Models. arXiv preprint arXiv:2406.14192(2024).","author":"Su Zhaochen","year":"2024","unstructured":"Zhaochen Su, Jun Zhang, Tong Zhu, Xiaoye Qu, Juntao Li, Min Zhang, and Yu Cheng. 2024. Timo: Towards Better Temporal Reasoning for Language Models. arXiv preprint arXiv:2406.14192(2024)."},{"key":"e_1_3_2_2_35_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_36_1","unstructured":"Qwen Team. 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":"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. In Advances in neural information processing systems. 24824-24837."},{"key":"e_1_3_2_2_38_1","volume-title":"What do we (think we) know about formulaic language? An evaluation of the current state of play. Annual review of applied linguistics","author":"Wray Alison","year":"2012","unstructured":"Alison Wray. 2012. What do we (think we) know about formulaic language? An evaluation of the current state of play. Annual review of applied linguistics, Vol. 32 (2012), 231-254."},{"key":"e_1_3_2_2_39_1","volume-title":"Travelplanner: A benchmark for real-world planning with language agents. arXiv preprint arXiv:2402.01622(2024).","author":"Xie Jian","year":"2024","unstructured":"Jian Xie, Kai Zhang, Jiangjie Chen, Tinghui Zhu, Renze Lou, Yuandong Tian, Yanghua Xiao, and Yu Su. 2024. Travelplanner: A benchmark for real-world planning with language agents. arXiv preprint arXiv:2402.01622(2024)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219824"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17674"},{"key":"e_1_3_2_2_42_1","volume-title":"International Conference on Learning Representations.","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2023. React: Synergizing reasoning and acting in language models. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_43_1","volume-title":"Yi: Open foundation models by 01. ai. arXiv preprint arXiv:2403.04652","author":"Young Alex","year":"2024","unstructured":"Alex Young, Bei Chen, Chao Li, Chengen Huang, Ge Zhang, Guanwei Zhang, Heng Li, Jiangcheng Zhu, Jianqun Chen, Jing Chang, et al., 2024. Yi: Open foundation models by 01. ai. arXiv preprint arXiv:2403.04652 (2024)."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2225812"},{"key":"e_1_3_2_2_45_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zi Lin Zhuohan Li Dacheng Li Eric Xing et al. 2023. Judging LLM-as-a-judge with MT-Bench and Chatbot Arena. arXiv preprint arXiv:2306.05685 (2023)."}],"event":{"name":"KDD '25: The 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Toronto ON Canada","acronym":"KDD '25","sponsor":["SIGKDD ACM Special Interest Group on Knowledge Discovery in Data","SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3711896.3737208","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T18:19:44Z","timestamp":1777573184000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3711896.3737208"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,3]]},"references-count":45,"alternative-id":["10.1145\/3711896.3737208","10.1145\/3711896"],"URL":"https:\/\/doi.org\/10.1145\/3711896.3737208","relation":{},"subject":[],"published":{"date-parts":[[2025,8,3]]},"assertion":[{"value":"2025-08-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}