{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T19:33:39Z","timestamp":1781379219125,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":118,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62272447,62332019,62461160309,62473356"],"award-info":[{"award-number":["62272447,62332019,62461160309,62473356"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Basic Research Program of Institute of Software Chinese Academy of Sciences","award":["ISCAS-JCMS-202404"],"award-info":[{"award-number":["ISCAS-JCMS-202404"]}]},{"name":"CAS Major Project","award":["CJJ-145-24-14"],"award-info":[{"award-number":["CJJ-145-24-14"]}]},{"name":"Science and Technology Innovation Key R&D Program of Chongqing","award":["CSTB2023TIAD-STX0027"],"award-info":[{"award-number":["CSTB2023TIAD-STX0027"]}]},{"name":"Beijing Natural Science Foundation Haidian Original Innovation Joint Fund","award":["L242060,L232028,L222008"],"award-info":[{"award-number":["L242060,L232028,L222008"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,28]]},"DOI":"10.1145\/3746059.3747598","type":"proceedings-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T07:49:12Z","timestamp":1758959352000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":9,"title":["SketchGPT: A Sketch-based Multimodal Interface for Application-Agnostic LLM Interaction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2639-0487","authenticated-orcid":false,"given":"Zeyuan","family":"Huang","sequence":"first","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7187-4414","authenticated-orcid":false,"given":"Cangjun","family":"Gao","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1494-3730","authenticated-orcid":false,"given":"Yaxian","family":"Shan","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3105-8597","authenticated-orcid":false,"given":"Haoxiang","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1082-0630","authenticated-orcid":false,"given":"Qingkun","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8576-1201","authenticated-orcid":false,"given":"Xiaoming","family":"Deng","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3999-7429","authenticated-orcid":false,"given":"Cuixia","family":"Ma","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2094-5680","authenticated-orcid":false,"given":"Yu-Kun","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science and Informatics, Cardiff University, Cardiff, Wales, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5774-1916","authenticated-orcid":false,"given":"Yong-Jin","family":"Liu","sequence":"additional","affiliation":[{"name":"CS Department, MOE-Key Laboratory of Pervasive Computing, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6598-419X","authenticated-orcid":false,"given":"Feng","family":"Tian","sequence":"additional","affiliation":[{"name":"Institute of software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3473-7189","authenticated-orcid":false,"given":"Guozhong","family":"Dai","sequence":"additional","affiliation":[{"name":"Institute of software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9320-4920","authenticated-orcid":false,"given":"Hongan","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Software, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"e_1_3_3_3_2_2","unstructured":"Josh Achiam Steven Adler Sandhini Agarwal Lama Ahmad Ilge Akkaya Florencia\u00a0Leoni Aleman Diogo Almeida Janko Altenschmidt Sam Altman Shyamal Anadkat et\u00a0al. 2023. Gpt-4 technical report. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.08774 (2023)."},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/1384429.1384449"},{"key":"e_1_3_3_3_4_2","unstructured":"Henry Alps. 2024. OpenManus: An open-source initiative to replicate the capabilities of the Manus AI agent. https:\/\/github.com\/henryalps\/OpenManus. Accessed: 2025-04-01."},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/1281500.1281527"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/1027527.1027713"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/985692.985764"},{"key":"e_1_3_3_3_8_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Asai Akari","year":"2024","unstructured":"Akari Asai, Zeqiu Wu, Yizhong Wang, Avirup Sil, and Hannaneh Hajishirzi. 2024. Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=hSyW5go0v8"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29720"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1145\/800250.807503"},{"key":"e_1_3_3_3_11_2","unstructured":"Holly Branigan and Jamie Pearson. 2006. Alignment in human-computer interaction. How people talk to computers robots and other artificial communication partners (2006) 140\u2013156."},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642320"},{"key":"e_1_3_3_3_13_2","first-page":"1585","volume-title":"International Joint Conference on Mechanics, Design Engineering & Advanced Manufacturing","author":"Calavia M\u00a0Bel\u00e9n","year":"2022","unstructured":"M\u00a0Bel\u00e9n Calavia, Teresa Blanco, Ana Serrano, Anna Biedermann, and Roberto Casas. 2022. Think-Sketch-Create: Improving Creative Expression Through Sketching. In International Joint Conference on Mechanics, Design Engineering & Advanced Manufacturing. Springer, 1585\u20131597."},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","unstructured":"Jorge\u00a0D. Camba Pedro Company and Ferran Naya. 2022. Sketch-Based Modeling in Mechanical Engineering Design: Current Status and Opportunities. Computer-Aided Design 150 (Sept. 2022) 103283. 10.1016\/j.cad.2022.103283","DOI":"10.1016\/j.cad.2022.103283"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3208806.3208811"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/2818346.2820752"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606741"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3501819"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/266180.266328"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","unstructured":"Denis Coquenet Cl\u00e9ment Chatelain and Thierry Paquet. 2023. End-to-End Handwritten Paragraph Text Recognition Using a Vertical Attention Network. IEEE Transactions on Pattern Analysis and Machine Intelligence 45 1 (2023) 508\u2013524. 10.1109\/TPAMI.2022.3144899","DOI":"10.1109\/TPAMI.2022.3144899"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-5041-2896-4_19"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580969"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1145\/3478384.3478423"},{"key":"e_1_3_3_3_24_2","first-page":"226","volume-title":"kdd","author":"Ester Martin","year":"1996","unstructured":"Martin Ester, Hans-Peter Kriegel, J\u00f6rg Sander, Xiaowei Xu, et\u00a0al. 1996. A density-based algorithm for discovering clusters in large spatial databases with noise. In kdd , Vol.\u00a096. 226\u2013231."},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/2807442.2807499"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/359784.360278"},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","unstructured":"Weiwei Gao Kexin Du Yujia Luo Weinan Shi Chun Yu and Yuanchun Shi. 2024. EasyAsk: An In-App Contextual Tutorial Search Assistant for Older Adults with Voice and Touch Inputs. Proc. ACM Interact. Mob. Wearable Ubiquitous Technol. 8 3 Article 102 (Sept. 2024) 27\u00a0pages. 10.1145\/3678516","DOI":"10.1145\/3678516"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","unstructured":"Ce Ge Haifeng Sun Yi-Zhe Song Zhanyu Ma and Jianxin Liao. 2022. Exploring Local Detail Perception for Scene Sketch Semantic Segmentation. IEEE Transactions on Image Processing 31 (2022) 1447\u20131461. 10.1109\/TIP.2022.3142511","DOI":"10.1109\/TIP.2022.3142511"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3452918.3458806"},{"key":"e_1_3_3_3_30_2","unstructured":"Google. 2024. Circle (or highlight or scribble) to Search. [Online]. https:\/\/blog.google\/products\/search\/google-circle-to-search-android\/ Accessed on April 14 2024."},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642699"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85412-823"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3650784"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/3708359.3712070"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/67449.67496"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Haoxiang Hu Cangjun Gao Yaokun Li Xiaoming Deng YuKun Lai Cuixia Ma Yong-Jin Liu and Hongan Wang. 2024. SpaceGTN: A Time-Agnostic Graph Transformer Network for Handwritten Diagram Recognition and Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence 38 3 (Mar. 2024) 2211\u20132219. 10.1609\/aaai.v38i3.27994","DOI":"10.1609\/aaai.v38i3.27994"},{"key":"e_1_3_3_3_37_2","unstructured":"Yushi Hu Weijia Shi Xingyu Fu Dan Roth Mari Ostendorf Luke Zettlemoyer Noah\u00a0A Smith and Ranjay Krishna. 2024. Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.09403 (2024)."},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","unstructured":"Junshi Huang Si Liu Junliang Xing Tao Mei and Shuicheng Yan. 2014. Circle & Search: Attribute-Aware Shoe Retrieval. ACM Trans. Multimedia Comput. Commun. Appl. 11 1 Article 3 (sep 2014) 21\u00a0pages. 10.1145\/2632165","DOI":"10.1145\/2632165"},{"key":"e_1_3_3_3_39_2","unstructured":"LangChain Inc.2024. Langgraph. [Online]. https:\/\/langchain-ai.github.io\/langgraph\/ Accessed on March 20 2024."},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/HRI61500.2025.10974033"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3503564"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606737"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.3115\/976909.979653"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/1330588.1330597"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/1240624.1240778"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706599.3720173"},{"key":"e_1_3_3_3_47_2","unstructured":"Hark-Joon Kim Hayoung Kim Seungho Chae Jonghoon Seo and Tack-Don Han. [n. d.]. AR Pen and Hand Gestures: A New Tool for Pen Drawings. Augmented Reality ([n. d.])."},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642693"},{"key":"e_1_3_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479938"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642230"},{"key":"e_1_3_3_3_51_2","unstructured":"lepo.co. 2024. WPF UI. [Online]. https:\/\/wpfui.lepo.co\/ Accessed on July 20 2024."},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/1095034.1095074"},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"publisher","unstructured":"Chunyuan Liao Fran\u00e7ois Guimbreti\u00e8re Ken Hinckley and Jim Hollan. 2008. Papiercraft: A gesture-based command system for interactive paper. ACM Trans. Comput.-Hum. Interact. 14 4 Article 18 (Jan. 2008) 27\u00a0pages. 10.1145\/1314683.1314686","DOI":"10.1145\/1314683.1314686"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713801"},{"key":"e_1_3_3_3_55_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642217"},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3580817"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","unstructured":"Shiyang Lu Tao Mei Jingdong Wang Jian Zhang Zhiyong Wang and Shipeng Li. 2015. Exploratory Product Image Search With Circle-to-Search Interaction. IEEE Transactions on Circuits and Systems for Video Technology 25 7 (2015) 1190\u20131202. 10.1109\/TCSVT.2014.2372272","DOI":"10.1109\/TCSVT.2014.2372272"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"crossref","unstructured":"Cui-Xia Ma Yong-Jin Liu Hong-An Wang Dong-Xing Teng and Guo-Zhong Dai. 2012. Sketch-based annotation and visualization in video authoring. IEEE Transactions on Multimedia 14 4 (2012) 1153\u20131165.","DOI":"10.1109\/TMM.2012.2190389"},{"key":"e_1_3_3_3_59_2","unstructured":"Manus Team. 2024. Manus: a general AI agent that bridges minds and actions. https:\/\/manus.im\/. Accessed: 2025-04-08."},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642462"},{"key":"e_1_3_3_3_61_2","unstructured":"Microsoft. 2024. Microsoft Azure Speech to Text Service. [Online]. https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/speech-service\/speech-to-text Accessed on March 14 2024."},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/1117309.1117345"},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3670947.3670969"},{"key":"e_1_3_3_3_64_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/711"},{"key":"e_1_3_3_3_65_2","unstructured":"OpenAI. 2024. OpenAI Platform. [Online]. https:\/\/platform.openai.com\/docs\/overview Accessed on August 20 2024."},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303163"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","unstructured":"Sharon Oviatt. 2000. Taming recognition errors with a multimodal interface. Commun. ACM 43 9 (Sept. 2000) 45\u201351. 10.1145\/348941.348979","DOI":"10.1145\/348941.348979"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"publisher","unstructured":"Sharon Oviatt and Philip Cohen. 2000. Perceptual user interfaces: multimodal interfaces that process what comes naturally. Commun. ACM 43 3 (March 2000) 45\u201353. 10.1145\/330534.330538","DOI":"10.1145\/330534.330538"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01036"},{"key":"e_1_3_3_3_70_2","doi-asserted-by":"publisher","DOI":"10.1145\/2642918.2647397"},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/VLHCC.2006.28"},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3584931.3606993"},{"key":"e_1_3_3_3_73_2","doi-asserted-by":"publisher","unstructured":"Fei-wei Qin Shu-ming Gao Xiao-ling Yang Jing Bai and Qu-hong Zhao. 2017. A Sketch-Based Semantic Retrieval Approach for 3D CAD Models. Applied Mathematics-A Journal of Chinese Universities 32 1 (March 2017) 27\u201352. 10.1007\/s11766-017-3450-3","DOI":"10.1007\/s11766-017-3450-3"},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3714310"},{"key":"e_1_3_3_3_75_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642024"},{"key":"e_1_3_3_3_76_2","unstructured":"Sebasti\u00e1n Ram\u00edrez. 2024. FastAPI. [Online]. https:\/\/fastapi.tiangolo.com\/ Accessed on March 12 2024."},{"key":"e_1_3_3_3_77_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411763.3451760"},{"key":"e_1_3_3_3_78_2","doi-asserted-by":"publisher","unstructured":"Laurel\u00a0D. Riek. 2012. Wizard of Oz studies in HRI: a systematic review and new reporting guidelines. J. Hum.-Robot Interact. 1 1 (jul 2012) 119\u2013136. 10.5898\/JHRI.1.1.Riek","DOI":"10.5898\/JHRI.1.1.Riek"},{"key":"e_1_3_3_3_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_3_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3651089"},{"key":"e_1_3_3_3_81_2","doi-asserted-by":"publisher","unstructured":"Sigurdur\u00a0Gauti Samuelsson and Matthias Book. 2020. Eliciting Sketched Expressions of Command Intentions in an IDE. Proc. ACM Hum.-Comput. Interact. 4 ISS Article 200 (Nov. 2020) 25\u00a0pages. 10.1145\/3427328","DOI":"10.1145\/3427328"},{"key":"e_1_3_3_3_82_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19839-7_15"},{"key":"e_1_3_3_3_83_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676444"},{"key":"e_1_3_3_3_84_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581469"},{"key":"e_1_3_3_3_85_2","series-title":"(NIPS \u201923)","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","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. In Proceedings of the 37th International Conference on Neural Information Processing Systems (New Orleans, LA, USA) (NIPS \u201923). Curran Associates Inc., Red Hook, NY, USA, Article 377, 19\u00a0pages."},{"key":"e_1_3_3_3_86_2","doi-asserted-by":"publisher","unstructured":"Ben Shneiderman. 2020. Human-Centered Artificial Intelligence: Reliable Safe & Trustworthy. International Journal of Human\u2013Computer Interaction 36 6 (2020) 495\u2013504. 10.1080\/10447318.2020.1741118 arXiv:10.1080\/10447318.2020.1741118","DOI":"10.1080\/10447318.2020.1741118"},{"key":"e_1_3_3_3_87_2","doi-asserted-by":"publisher","DOI":"10.1007\/11555261_24"},{"key":"e_1_3_3_3_88_2","doi-asserted-by":"publisher","DOI":"10.1145\/3490099.3511161"},{"key":"e_1_3_3_3_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474792"},{"key":"e_1_3_3_3_90_2","unstructured":"Al Sweigart. 2024. PyAutoGUI: Cross-platform GUI Automation for Human Beings. [Online]. https:\/\/github.com\/asweigart\/pyautogui\/tree\/master Accessed on September 1 2024."},{"key":"e_1_3_3_3_91_2","unstructured":"CAMEL-AI Team. 2024. Owl: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation. https:\/\/github.com\/camel-ai\/owl. Accessed: 2025-04-01."},{"key":"e_1_3_3_3_92_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA52953.2021.00141"},{"key":"e_1_3_3_3_93_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445721"},{"key":"e_1_3_3_3_94_2","doi-asserted-by":"publisher","unstructured":"Emmanuel Turquin Jamie Wither Laurence Boissieux Marie-paule Cani and John Hughes. 2007. A Sketch-Based Interface for Clothing Virtual Characters. IEEE Computer Graphics and Applications 27 1 (Jan. 2007) 72\u201381. 10.1109\/MCG.2007.1","DOI":"10.1109\/MCG.2007.1"},{"key":"e_1_3_3_3_95_2","unstructured":"Unsplash. 2024. Beautiful Free Images & Pictures | Unsplash. [Online]. https:\/\/unsplash.com Accessed on September 1 2024."},{"key":"e_1_3_3_3_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643834.3661525"},{"key":"e_1_3_3_3_97_2","doi-asserted-by":"crossref","unstructured":"Ilse\u00a0M Verstijnen Cees van Leeuwen Gabriela Goldschmidt Ronald Hamel and JM Hennessey. 1998. Sketching and creative discovery. Design studies 19 4 (1998) 519\u2013546.","DOI":"10.1016\/S0142-694X(98)00017-9"},{"key":"e_1_3_3_3_98_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642865"},{"key":"e_1_3_3_3_99_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581402"},{"key":"e_1_3_3_3_100_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642803"},{"key":"e_1_3_3_3_101_2","first-page":"24824","volume-title":"Advances in Neural Information Processing Systems","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, Dale Schuurmans, Maarten Bosma, brian ichter, Fei Xia, Ed Chi, Quoc\u00a0V Le, and Denny Zhou. 2022. Chain-of-Thought Prompting Elicits Reasoning in Large Language Models. In Advances in Neural Information Processing Systems , S.\u00a0Koyejo, S.\u00a0Mohamed, A.\u00a0Agarwal, D.\u00a0Belgrave, K.\u00a0Cho, and A.\u00a0Oh (Eds.), Vol.\u00a035. Curran Associates, Inc., 24824\u201324837. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/9d5609613524ecf4f15af0f7b31abca4-Paper-Conference.pdf"},{"key":"e_1_3_3_3_102_2","doi-asserted-by":"publisher","DOI":"10.1145\/1358628.1358682"},{"key":"e_1_3_3_3_103_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491101.3519729"},{"key":"e_1_3_3_3_104_2","doi-asserted-by":"publisher","DOI":"10.1145\/3491102.3517582"},{"key":"e_1_3_3_3_105_2","doi-asserted-by":"crossref","unstructured":"Zhiheng Xi Wenxiang Chen Xin Guo Wei He Yiwen Ding Boyang Hong Ming Zhang Junzhe Wang Senjie Jin Enyu Zhou et\u00a0al. 2025. The rise and potential of large language model based agents: A survey. Science China Information Sciences 68 2 (2025) 121101.","DOI":"10.1007\/s11432-024-4222-0"},{"key":"e_1_3_3_3_106_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02444-3_13"},{"key":"e_1_3_3_3_107_2","doi-asserted-by":"publisher","DOI":"10.1145\/3672539.3686324"},{"key":"e_1_3_3_3_108_2","doi-asserted-by":"publisher","DOI":"10.1145\/3706598.3713822"},{"key":"e_1_3_3_3_109_2","doi-asserted-by":"publisher","DOI":"10.1145\/2642918.2647390"},{"key":"e_1_3_3_3_110_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581388"},{"key":"e_1_3_3_3_111_2","unstructured":"Shane\u00a0W Zamora and Eyr\u00fan\u00a0A Eyj\u00f3lfsd\u00f3ttir. [n. d.]. CircuitBoard: Sketch-Based Circuit Design and Analysis. ([n. d.])."},{"key":"e_1_3_3_3_112_2","doi-asserted-by":"publisher","unstructured":"Xin Zeng Xiaoyu Wang Tengxiang Zhang Chun Yu Shengdong Zhao and Yiqiang Chen. 2024. GestureGPT: Toward Zero-Shot Free-Form Hand Gesture Understanding with Large Language Model Agents. Proc. ACM Hum.-Comput. Interact. 8 ISS Article 545 (Oct. 2024) 38\u00a0pages. 10.1145\/3698145","DOI":"10.1145\/3698145"},{"key":"e_1_3_3_3_113_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_3_114_2","unstructured":"Yusen Zhang Ruoxi Sun Yanfei Chen Tomas Pfister Rui Zhang and Sercan Arik. 2024. Chain of agents: Large language models collaborating on long-context tasks. Advances in Neural Information Processing Systems 37 (2024) 132208\u2013132237."},{"key":"e_1_3_3_3_115_2","unstructured":"Zhuosheng Zhang Aston Zhang Mu Li hai zhao George Karypis and Alex Smola. 2024. Multimodal Chain-of-Thought Reasoning in Language Models. Transactions on Machine Learning Research (2024). https:\/\/openreview.net\/forum?id=y1pPWFVfvR"},{"key":"e_1_3_3_3_116_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413633"},{"key":"e_1_3_3_3_117_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611462"},{"key":"e_1_3_3_3_118_2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/202"},{"key":"e_1_3_3_3_119_2","doi-asserted-by":"crossref","unstructured":"Gustavo Zurita Nelson Baloian and Felipe Baytelman. 2008. A collaborative face-to-face design support system based on sketching and gesturing. Advanced Engineering Informatics 22 3 (2008) 340\u2013349.","DOI":"10.1016\/j.aei.2007.09.003"}],"event":{"name":"UIST '25: The 38th Annual ACM Symposium on User Interface Software and Technology","location":"Busan Republic of Korea","acronym":"UIST '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746059.3747598","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:03:39Z","timestamp":1759010619000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746059.3747598"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":118,"alternative-id":["10.1145\/3746059.3747598","10.1145\/3746059"],"URL":"https:\/\/doi.org\/10.1145\/3746059.3747598","relation":{},"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"2025-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}