{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:31:54Z","timestamp":1772040714341,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T00:00:00Z","timestamp":1720569600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,7,10]]},"DOI":"10.1145\/3626772.3661381","type":"proceedings-article","created":{"date-parts":[[2024,7,11]],"date-time":"2024-07-11T12:40:05Z","timestamp":1720701605000},"page":"2983-2986","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Empowering Large Language Models: Tool Learning for Real-World Interaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5027-0138","authenticated-orcid":false,"given":"Hongru","family":"Wang","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3608-5061","authenticated-orcid":false,"given":"Yujia","family":"Qin","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9182-8158","authenticated-orcid":false,"given":"Yankai","family":"Lin","sequence":"additional","affiliation":[{"name":"Renmin University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9779-2088","authenticated-orcid":false,"given":"Jeff Z.","family":"Pan","sequence":"additional","affiliation":[{"name":"University of Edinburgh, Edinburgh, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9427-5659","authenticated-orcid":false,"given":"Kam-Fai","family":"Wong","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Hong Kong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,7,11]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Concrete problems in AI safety. arXiv preprint arXiv:1606.06565","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei, Chris Olah, Jacob Steinhardt, Paul Christiano, John Schulman, and Dan Man\u00e9. 2016. Concrete problems in AI safety. arXiv preprint arXiv:1606.06565 (2016)."},{"key":"e_1_3_2_1_2_1","unstructured":"Akari Asai Zeqiu Wu Yizhong Wang Avirup Sil and Hannaneh Hajishirzi. 2023. Self-RAG: Learning to Retrieve Generate and Critique through Self-Reflection. arXiv:2310.11511 [cs.CL]"},{"key":"e_1_3_2_1_3_1","volume-title":"Precursors to a theory of mind: Understanding attention in others. Natural theories of mind: Evolution, development and simulation of everyday mindreading 1","author":"Baron-Cohen Simon","year":"1991","unstructured":"Simon Baron-Cohen. 1991. Precursors to a theory of mind: Understanding attention in others. Natural theories of mind: Evolution, development and simulation of everyday mindreading 1 (1991), 233--251."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"crossref","unstructured":"Yupeng Chang Xu Wang Jindong Wang Yuan Wu Linyi Yang Kaijie Zhu Hao Chen Xiaoyuan Yi Cunxiang Wang Yidong Wang Wei Ye Yue Zhang Yi Chang Philip S. Yu Qiang Yang and Xing Xie. 2023. A Survey on Evaluation of Large Language Models. arXiv:2307.03109 [cs.CL]","DOI":"10.1145\/3641289"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3594246"},{"key":"e_1_3_2_1_6_1","volume-title":"reflection, reflection. I'm thinking all the time, why do I need a theory or model of reflection?'. Developing Reflective Practice: A guide for beginning teachers","author":"Dye Vanessa","year":"2011","unstructured":"Vanessa Dye. 2011. Reflection, reflection, reflection. I'm thinking all the time, why do I need a theory or model of reflection?'. Developing Reflective Practice: A guide for beginning teachers. Maidenhead: McGraw-Hill Education (2011), 217--234."},{"key":"e_1_3_2_1_7_1","volume-title":"Theory of mind. Current biology 15, 17","author":"Frith Chris","year":"2005","unstructured":"Chris Frith and Uta Frith. 2005. Theory of mind. Current biology 15, 17 (2005), R644-R645."},{"key":"e_1_3_2_1_8_1","unstructured":"Yao Fu Rameswar Panda Xinyao Niu Xiang Yue Hannaneh Hajishirzi Yoon Kim and Hao Peng. 2024. Data Engineering for Scaling Language Models to 128K Context. arXiv:2402.10171 [cs.CL]"},{"key":"e_1_3_2_1_9_1","volume-title":"PAL: Program-aided Language Models. arXiv:2211.10435 [cs.CL]","author":"Gao Luyu","year":"2023","unstructured":"Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. PAL: Program-aided Language Models. arXiv:2211.10435 [cs.CL]"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.364"},{"key":"e_1_3_2_1_11_1","volume-title":"From tools to theories: Aheuristic of discovery in cognitive psychology. Psychological review 98, 2","author":"Gigerenzer Gerd","year":"1991","unstructured":"Gerd Gigerenzer. 1991. From tools to theories: Aheuristic of discovery in cognitive psychology. Psychological review 98, 2 (1991), 254."},{"key":"e_1_3_2_1_12_1","unstructured":"Shibo Hao Tianyang Liu Zhen Wang and Zhiting Hu. 2024. ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings. arXiv:2305.11554 [cs.CL]"},{"key":"e_1_3_2_1_13_1","volume-title":"Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and J\u00fcrgen Schmidhuber.","author":"Hong Sirui","year":"2023","unstructured":"Sirui Hong, Mingchen Zhuge, Jonathan Chen, Xiawu Zheng, Yuheng Cheng, Ceyao Zhang, Jinlin Wang, Zili Wang, Steven Ka Shing Yau, Zijuan Lin, Liyang Zhou, Chenyu Ran, Lingfeng Xiao, Chenglin Wu, and J\u00fcrgen Schmidhuber. 2023. MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework. arXiv:2308.00352 [cs.AI]"},{"key":"e_1_3_2_1_14_1","volume-title":"Planning","author":"Huang Shijue","unstructured":"Shijue Huang, Wanjun Zhong, Jianqiao Lu, Qi Zhu, Jiahui Gao, Weiwen Liu, Yutai Hou, Xingshan Zeng, Yasheng Wang, Lifeng Shang, Xin Jiang, Ruifeng Xu, and Qun Liu. 2024. Planning, Creation, Usage: Benchmarking LLMs for Comprehensive Tool Utilization in Real-World Complex Scenarios. arXiv:2401.17167 [cs.CL]"},{"key":"e_1_3_2_1_15_1","unstructured":"Wenlong Huang Pieter Abbeel Deepak Pathak and Igor Mordatch. 2022. Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents. arXiv:2201.07207 [cs.LG]"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-industry.4"},{"key":"e_1_3_2_1_17_1","volume-title":"Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback. arXiv preprint arXiv:2303.05453","author":"Kirk Hannah Rose","year":"2023","unstructured":"Hannah Rose Kirk, Bertie Vidgen, Paul R\u00f6ttger, and Scott A Hale. 2023. Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback. arXiv preprint arXiv:2303.05453 (2023)."},{"key":"e_1_3_2_1_18_1","volume-title":"Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela.","author":"Lewis Patrick","year":"2021","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2021. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. arXiv:2005.11401 [cs.CL]"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Jacky Liang Wenlong Huang Fei Xia Peng Xu Karol Hausman Brian Ichter Pete Florence and Andy Zeng. 2023. Code as Policies: Language Model Programs for Embodied Control. arXiv:2209.07753 [cs.RO]","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"e_1_3_2_1_20_1","unstructured":"Bill Yuchen Lin Yicheng Fu Karina Yang Faeze Brahman Shiyu Huang Chandra Bhagavatula Prithviraj Ammanabrolu Yejin Choi and Xiang Ren. 2023. Swift-Sage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks. arXiv:2305.17390 [cs.CL]"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Xiao Liu Hanyu Lai Hao Yu Yifan Xu Aohan Zeng Zhengxiao Du Peng Zhang Yuxiao Dong and Jie Tang. 2023. WebGLM: Towards An Efficient Web-Enhanced Question Answering System with Human Preferences. arXiv:2306.07906 [cs.CL]","DOI":"10.1145\/3580305.3599931"},{"key":"e_1_3_2_1_22_1","volume-title":"Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models. arXiv:2402.17177 [cs.CV]","author":"Liu Yixin","year":"2024","unstructured":"Yixin Liu, Kai Zhang, Yuan Li, Zhiling Yan, Chujie Gao, Ruoxi Chen, Zhengqing Yuan, Yue Huang, Hanchi Sun, Jianfeng Gao, Lifang He, and Lichao Sun. 2024. Sora: A Review on Background, Technology, Limitations, and Opportunities of Large Vision Models. arXiv:2402.17177 [cs.CV]"},{"key":"e_1_3_2_1_23_1","volume-title":"Song-Chun Zhu, and Jianfeng Gao.","author":"Lu Pan","year":"2023","unstructured":"Pan Lu, Baolin Peng, Hao Cheng, Michel Galley, Kai-Wei Chang, Ying Nian Wu, Song-Chun Zhu, and Jianfeng Gao. 2023. Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models. arXiv:2304.09842 [cs.CL]"},{"key":"e_1_3_2_1_24_1","unstructured":"Reiichiro Nakano Jacob Hilton Suchir Balaji Jeff Wu Long Ouyang Christina Kim Christopher Hesse Shantanu Jain Vineet Kosaraju William Saunders Xu Jiang Karl Cobbe Tyna Eloundou Gretchen Krueger Kevin Button Matthew Knight Benjamin Chess and John Schulman. 2022. WebGPT: Browser-assisted question-answering with human feedback. arXiv:2112.09332 [cs.CL]"},{"key":"e_1_3_2_1_25_1","volume-title":"TALM: Tool Augmented Language Models. arXiv:2205.12255 [cs.CL]","author":"Parisi Aaron","year":"2022","unstructured":"Aaron Parisi, Yao Zhao, and Noah Fiedel. 2022. TALM: Tool Augmented Language Models. arXiv:2205.12255 [cs.CL]"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Xavier Puig Kevin Ra Marko Boben Jiaman Li Tingwu Wang Sanja Fidler and Antonio Torralba. 2018. VirtualHome: Simulating Household Activities via Programs. arXiv:1806.07011 [cs.CV]","DOI":"10.1109\/CVPR.2018.00886"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Yujia Qin Shengding Hu Yankai Lin Weize Chen Ning Ding Ganqu Cui Zheni Zeng Yufei Huang Chaojun Xiao Chi Han Yi Ren Fung Yusheng Su Huadong Wang Cheng Qian Runchu Tian Kunlun Zhu Shihao Liang Xingyu Shen Bokai Xu Zhen Zhang Yining Ye Bowen Li Ziwei Tang Jing Yi Yuzhang Zhu Zhenning Dai Lan Yan Xin Cong Yaxi Lu Weilin Zhao Yuxiang Huang Junxi Yan Xu Han Xian Sun Dahai Li Jason Phang Cheng Yang Tongshuang Wu Heng Ji Zhiyuan Liu and Maosong Sun. 2023. Tool Learning with Foundation Models. arXiv:2304.08354 [cs.CL]","DOI":"10.1145\/3704435"},{"key":"e_1_3_2_1_28_1","volume-title":"Toolformer: Language Models Can Teach Themselves to Use Tools. arXiv:2302.04761 [cs.CL]","author":"Schick Timo","year":"2023","unstructured":"Timo Schick, Jane Dwivedi-Yu, Roberto Dess\u00ec, Roberta Raileanu, Maria Lomeli, Luke Zettlemoyer, Nicola Cancedda, and Thomas Scialom. 2023. Toolformer: Language Models Can Teach Themselves to Use Tools. arXiv:2302.04761 [cs.CL]"},{"key":"e_1_3_2_1_29_1","unstructured":"Yongliang Shen Kaitao Song Xu Tan Dongsheng Li Weiming Lu and Yueting Zhuang. 2023. HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face. arXiv:2303.17580 [cs.CL]"},{"key":"e_1_3_2_1_30_1","unstructured":"Mohit Shridhar Xingdi Yuan Marc-Alexandre C\u00f4t\u00e9 Yonatan Bisk Adam Trischler and Matthew Hausknecht. 2021. ALFWorld: Aligning Text and Embodied Environments for Interactive Learning. arXiv:2010.03768 [cs.CL]"},{"key":"e_1_3_2_1_31_1","volume-title":"Paolo Rota, and Nicu Sebe.","author":"Soviany Petru","year":"2022","unstructured":"Petru Soviany, Radu Tudor Ionescu, Paolo Rota, and Nicu Sebe. 2022. Curriculum Learning: A Survey. arXiv:2101.10382 [cs.LG]"},{"key":"e_1_3_2_1_32_1","volume-title":"Griffiths","author":"Sumers Theodore R.","year":"2023","unstructured":"Theodore R. Sumers, Shunyu Yao, Karthik Narasimhan, and Thomas L. Griffiths. 2023. Cognitive Architectures for Language Agents. arXiv:2309.02427 [cs.AI]"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"D\u00eddac Sur\u00eds Sachit Menon and Carl Vondrick. 2023. ViperGPT: Visual Inference via Python Execution for Reasoning. arXiv:2303.08128 [cs.CV]","DOI":"10.1109\/ICCV51070.2023.01092"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.641"},{"key":"e_1_3_2_1_35_1","unstructured":"Hongru Wang Wenyu Huang Yang Deng Rui Wang Zezhong Wang Yufei Wang Fei Mi Jeff Z. Pan and Kam-Fai Wong. 2024. UniMS-RAG: A Unified Multi-source Retrieval-Augmented Generation for Personalized Dialogue Systems. arXiv:2401.13256 [cs.CL]"},{"key":"e_1_3_2_1_36_1","volume-title":"TPE: Towards Better Compositional Reasoning over Conceptual Tools with Multi-persona Collaboration. arXiv:2309.16090 [cs.AI]","author":"Wang Hongru","year":"2023","unstructured":"Hongru Wang, Huimin Wang, Lingzhi Wang, Minda Hu, Rui Wang, Boyang Xue, Hongyuan Lu, Fei Mi, and Kam-Fai Wong. 2023. TPE: Towards Better Compositional Reasoning over Conceptual Tools with Multi-persona Collaboration. arXiv:2309.16090 [cs.AI]"},{"key":"e_1_3_2_1_37_1","unstructured":"Hongru Wang Lingzhi Wang Yiming Du Liang Chen Jingyan Zhou Yufei Wang and Kam-Fai Wong. 2023. A Survey of the Evolution of Language Model-Based Dialogue Systems. arXiv:2311.16789 [cs.CL]"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.806"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Hongru Wang Boyang Xue Baohang Zhou Tianhua Zhang Cunxiang Wang Guanhua Chen Huimin Wang and Kam fai Wong. 2024. Self-DC: When to retrieve and When to generate? Self Divide-and-Conquer for Compositional Unknown Questions. arXiv:2402.13514 [cs.CL]","DOI":"10.18653\/v1\/2025.naacl-long.331"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.775"},{"key":"e_1_3_2_1_41_1","unstructured":"Rongwu Xu Zehan Qi Cunxiang Wang Hongru Wang Yue Zhang and Wei Xu. 2024. Knowledge Conflicts for LLMs: A Survey. arXiv:2403.08319 [cs.CL]"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.525"},{"key":"e_1_3_2_1_43_1","unstructured":"Wayne Xin Zhao Kun Zhou Junyi Li Tianyi Tang Xiaolei Wang Yupeng Hou Yingqian Min Beichen Zhang Junjie Zhang Zican Dong Yifan Du Chen Yang Yushuo Chen Zhipeng Chen Jinhao Jiang Ruiyang Ren Yifan Li Xinyu Tang Zikang Liu Peiyu Liu Jian-Yun Nie and Ji-Rong Wen. 2023. A Survey of Large Language Models. arXiv:2303.18223 [cs.CL]"}],"event":{"name":"SIGIR 2024: The 47th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Washington DC USA","acronym":"SIGIR 2024","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3661381","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3626772.3661381","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T05:25:31Z","timestamp":1755840331000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3626772.3661381"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,10]]},"references-count":43,"alternative-id":["10.1145\/3626772.3661381","10.1145\/3626772"],"URL":"https:\/\/doi.org\/10.1145\/3626772.3661381","relation":{},"subject":[],"published":{"date-parts":[[2024,7,10]]},"assertion":[{"value":"2024-07-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}