{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T09:05:53Z","timestamp":1769504753711,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":73,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001029","name":"Department of Defence, Australian Government","doi-asserted-by":"publisher","award":["MyIP8655, ID9024"],"award-info":[{"award-number":["MyIP8655, ID9024"]}],"id":[{"id":"10.13039\/501100001029","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["FT180100447"],"award-info":[{"award-number":["FT180100447"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,13]]},"DOI":"10.1145\/3716553.3750799","type":"proceedings-article","created":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T13:13:16Z","timestamp":1760188396000},"page":"550-560","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["When Words Fall Short: The Case for Conversational Interfaces that Don\u2019t Listen"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7782-8656","authenticated-orcid":false,"given":"James","family":"Simpson","sequence":"first","affiliation":[{"name":"School of Psychological Sciences, Macquarie University, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7191-8140","authenticated-orcid":false,"given":"Hamish","family":"Stening","sequence":"additional","affiliation":[{"name":"School of Psychological Sciences, Macquarie University, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0608-0403","authenticated-orcid":false,"given":"Gaurav","family":"Patil","sequence":"additional","affiliation":[{"name":"School of Psychological Sciences, Macquarie University, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1719-8044","authenticated-orcid":false,"given":"Patrick","family":"Nalepka","sequence":"additional","affiliation":[{"name":"School of Psychological Sciences, Macquarie University, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9908-7182","authenticated-orcid":false,"given":"Mark","family":"Dras","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0031-737X","authenticated-orcid":false,"given":"Rachel","family":"W Kallen","sequence":"additional","affiliation":[{"name":"School of Psychological Sciences, Macquarie University, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9241-2878","authenticated-orcid":false,"given":"Simon","family":"G Hosking","sequence":"additional","affiliation":[{"name":"Defence Science and Technology Group, Australian Department of Defence, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9159-2774","authenticated-orcid":false,"given":"Michael","family":"J Richardson","sequence":"additional","affiliation":[{"name":"School of Psychological Sciences, Macquarie University, Sydney, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7363-1511","authenticated-orcid":false,"given":"Deborah","family":"Richards","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}]}],"member":"320","published-online":{"date-parts":[[2025,10,12]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.448"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3469595.3469608"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570945.3607305"},{"key":"e_1_3_3_3_5_2","unstructured":"Saptarashmi Bandyopadhyay Vikas Bahirwani Lavisha Aggarwal Bhanu Guda Lin Li and Andrea Colaco. 2025. YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks. arxiv:https:\/\/arXiv.org\/abs\/2501.09355\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2501.09355"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICHMS53169.2021.9582626"},{"key":"e_1_3_3_3_7_2","unstructured":"Mariusz Bojarski Davide\u00a0Del Testa Daniel Dworakowski Bernhard Firner Beat Flepp Prasoon Goyal Lawrence\u00a0D. Jackel Mathew Monfort Urs Muller Jiakai Zhang Xin Zhang Jake Zhao and Karol Zieba. 2016. End to End Learning for Self-Driving Cars. https:\/\/arxiv.org\/abs\/1604.07316v1"},{"key":"e_1_3_3_3_8_2","unstructured":"Tom\u00a0B Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell Sandhini Agarwal Ariel Herbert-Voss Gretchen Krueger Tom Henighan Rewon Child Aditya Ramesh Daniel\u00a0M Ziegler Jeffrey Wu Clemens Winter Christopher Hesse Mark Chen Eric Sigler Mateusz Litwin Scott Gray Benjamin Chess Jack Clark Christopher Berner Sam McCandlish Alec Radford Ilya Sutskever and Dario Amodei. 2020. Language Models are Few-Shot Learners. Advances in Neural Information Processing Systems 33 (2020) 1877\u20131901. https:\/\/commoncrawl.org\/the-data\/"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1547"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.5555\/3635637.3662871"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376789"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2262"},{"key":"e_1_3_3_3_13_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique\u00a0Ponde de Oliveira\u00a0Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe\u00a0Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William\u00a0Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew\u00a0N. Carr Jan Leike Josh Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. arxiv:https:\/\/arXiv.org\/abs\/2107.03374\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2107.03374"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","unstructured":"ChenHongshen LiuXiaorui YinDawei and TangJiliang. 2017. A Survey on Dialogue Systems. ACM SIGKDD Explorations Newsletter 19 (11 2017) 25\u201335. Issue 2. 10.1145\/3166054.3166058","DOI":"10.1145\/3166054.3166058"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1998-260"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","unstructured":"Mustafa Demir Nathan\u00a0J. McNeese and Nancy\u00a0J. Cooke. 2019. The Evolution of Human-Autonomy Teams in Remotely Piloted Aircraft Systems Operations. Frontiers in Communication 4 (2019) 50. 10.3389\/FCOMM.2019.00050\/BIBTEX","DOI":"10.3389\/FCOMM.2019.00050\/BIBTEX"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","unstructured":"Mustafa Demir Nathan\u00a0J. McNeese Nancy\u00a0J. Cooke Jerry\u00a0T. Ball Christopher Myers and Marry Friedman. 2016. Synthetic Teammate Communication and Coordination With Humans. http:\/\/dx.doi.org\/10.1177\/1541931215591275 2015-January (12 2016) 951\u2013955. 10.1177\/1541931215591275","DOI":"10.1177\/1541931215591275"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.18653\/V1\/N19-1423"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","unstructured":"Jurriaan\u00a0Van Diggelen Tijmen Muller and Karel Van\u00a0Den Bosch. 2010. Using artificial team members for team training in virtual environments. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) 6356 LNAI (2010) 28\u201334. 10.1007\/978-3-642-15892-63\/COVER","DOI":"10.1007\/978-3-642-15892-63\/COVER"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342775.3342794"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","unstructured":"Foteini Filippidou and Lefteris Moussiades. 2020. A benchmarking of IBM google and wit automatic speech recognition systems. IFIP Advances in Information and Communication Technology 583 IFIP (2020) 73\u201382. 10.1007\/978-3-030-49161-17\/TABLES\/4","DOI":"10.1007\/978-3-030-49161-17\/TABLES\/4"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"key":"e_1_3_3_3_23_2","volume-title":"Google Assistant is integrated with Android Auto and compatible cars","year":"2022","unstructured":"Google. 2022. Google Assistant is integrated with Android Auto and compatible cars. https:\/\/assistant.google.com\/platforms\/cars\/"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1177\/154193120605000909"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","unstructured":"Sandra\u00a0G. Hart and Lowell\u00a0E. Staveland. 1988. Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research. Advances in Psychology 52 (1 1988) 139\u2013183. Issue C. 10.1016\/S0166-4115(08)62386-9","DOI":"10.1016\/S0166-4115(08)62386-9"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581066"},{"key":"e_1_3_3_3_27_2","unstructured":"Edward\u00a0J. 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:https:\/\/arXiv.org\/abs\/2106.09685\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2106.09685"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1145\/3434073.3444671"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","unstructured":"Carolin Ischen Theo\u00a0B. Araujo Hilde\u00a0A.M. Voorveld Guda\u00a0Van Noort and Edith\u00a0G. Smit. 2022. Is voice really persuasive? The influence of modality in virtual assistant interactions and two alternative explanations. Internet Research 32 (12 2022) 402\u2013425. Issue 7. 10.1108\/INTR-03-2022-0160\/FULL\/PDF","DOI":"10.1108\/INTR-03-2022-0160\/FULL\/PDF"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342775.3342805"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","unstructured":"J.\u00a0F. Kelley. 1984. An iterative design methodology for user-friendly natural language office information applications. ACM Transactions on Information Systems (TOIS) 2 (1 1984) 26\u201341. Issue 1. 10.1145\/357417.357420","DOI":"10.1145\/357417.357420"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","unstructured":"Alice Kerly and Susan Bull. 2006. The potential for chatbots in negotiated learner modelling: A Wizard-of-Oz study. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) 4053 LNCS (2006) 443\u2013452. 10.1007\/1177430344\/COVER","DOI":"10.1007\/1177430344\/COVER"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","unstructured":"Yann Lecun Yoshua Bengio and Geoffrey Hinton. 2015. Deep learning. Nature 2015 521:7553 521 (5 2015) 436\u2013444. Issue 7553. 10.1038\/nature14539","DOI":"10.1038\/nature14539"},{"key":"e_1_3_3_3_34_2","unstructured":"Bo Li Yuanhan Zhang Liangyu Chen Jinghao Wang Fanyi Pu Jingkang Yang Chunyuan Li and Ziwei Liu. 2023. MIMIC-IT: Multi-Modal In-Context Instruction Tuning. arxiv:https:\/\/arXiv.org\/abs\/2306.05425\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2306.05425"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","unstructured":"Ting\u00a0En Lin Yuchuan Wu Fei Huang Luo Si Jian Sun and Yongbin Li. 2022. Duplex Conversation: Towards Human-like Interaction in Spoken Dialogue Systems. Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 22 (8 2022) 3299\u20133308. 10.1145\/3534678.3539209","DOI":"10.1145\/3534678.3539209"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Xingkun Liu Arash Eshghi Pawel Swietojanski and Verena Rieser. 2021. Benchmarking Natural Language Understanding Services for Building Conversational Agents. Lecture Notes in Electrical Engineering 714 (2021) 165\u2013183. 10.1007\/978-981-15-9323-915\/TABLES\/8","DOI":"10.1007\/978-981-15-9323-915\/TABLES\/8"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN50785.2021.9515464"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/2858036.2858288"},{"key":"e_1_3_3_3_39_2","unstructured":"Sarah Mennicken R. Brillman Jennifer Thom-Santelli and H. Cramer. 2018. Challenges and Methods in Design of Domain-specific Voice Assistants."},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","unstructured":"Marie Meteer Meghan Hickey Ellen\u00a0Eide Kislal David Nahamoo and Carmi Rothberg. 2019. Are the Tools up to the Task? an Evaluation of Commercial Dialog Tools in Developing Conversational Enterprise-grade Dialog Systems. NAACL HLT 2019 - 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference 2 (2019) 106\u2013113. 10.18653\/V1\/N19-2014","DOI":"10.18653\/V1\/N19-2014"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","unstructured":"G. Molina\u00a0Le\u00f3n M. Lischka W. Luo and A. Breiter. 2022. Mobile and Multimodal? A Comparative Evaluation of Interactive Workplaces for Visual Data Exploration. Computer Graphics Forum 41 3 (2022) 417\u2013428. arXiv:https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.1455110.1111\/cgf.14551","DOI":"10.1111\/cgf.14551"},{"key":"e_1_3_3_3_42_2","series-title":"(NIPS \u201923)","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Mu Yao","year":"2023","unstructured":"Yao Mu, Qinglong Zhang, Mengkang Hu, Wenhai Wang, Mingyu Ding, Jun Jin, Bin Wang, Jifeng Dai, Yu Qiao, and Ping Luo. 2023. EmbodiedGPT: vision-language pre-training via embodied chain of thought. 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 1090, 14\u00a0pages."},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3469595.3469613"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","unstructured":"Patrick Nalepka Rachel\u00a0W. Kallen Anthony Chemero Elliot Saltzman and Michael\u00a0J. Richardson. 2017. Herd Those Sheep: Emergent Multiagent Coordination and Behavioral-Mode Switching. Psychological Science 28 5 (2017) 630\u2013650. 10.1177\/0956797617692107","DOI":"10.1177\/0956797617692107"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","unstructured":"Patrick Nalepka Matthew Prants Hamish Stening James Simpson Rachel\u00a0W Kallen Mark Dras Erik\u00a0D Reichle Simon\u00a0G Hosking Christopher Best and Michael\u00a0J Richardson. 2022. Assessing team effectiveness by how players structure their search in a first-person multiplayer video game. Cognitive Science 46 (10 2022) 1\u201332. Issue 10. 10.1111\/cogs.13204","DOI":"10.1111\/cogs.13204"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1537"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3610661.3617166"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","unstructured":"Anja\u00a0B. Naumann Ina Wechsung and J\u00f6rn Hurtienne. 2010. Multimodal interaction: A suitable strategy for including older users? Interacting with Computers 22 6 (09 2010) 465\u2013474. arXiv:https:\/\/academic.oup.com\/iwc\/article-pdf\/22\/6\/465\/2227674\/iwc22-0465.pdf10.1016\/j.intcom.2010.08.005","DOI":"10.1016\/j.intcom.2010.08.005"},{"key":"e_1_3_3_3_49_2","unstructured":"Erik Nijkmap Bo Pang Hiroaki Hayashi Lifu Tu Huan Wang Yingbo Zhou Silvio Savarese and Caiming Xiong. 2023. CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis | OpenReview. https:\/\/openreview.net\/forum?id=iaYcJKpY2B_"},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/258549.258821"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-5912"},{"key":"e_1_3_3_3_52_2","unstructured":"John\u00a0S\u00f6ren Pettersson and Malin Wik. 2014. Perspectives on Ozlab in the cloud: A literature review of tools supporting Wizard-of-Oz experimentation including an historical overview of 1971-2013 and notes on methodological issues and supporting generic tools."},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1145\/3405755.3406168"},{"key":"e_1_3_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3342775.3342796"},{"key":"e_1_3_3_3_55_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 (7 2012) 119\u2013136. Issue 1. 10.5898\/JHRI.1.1.Riek","DOI":"10.5898\/JHRI.1.1.Riek"},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.5555\/3398761.3398893"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.398"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"publisher","DOI":"10.1145\/3405755.3406166"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"publisher","unstructured":"James Simpson Patrick Nalepka Rachel\u00a0W Kallen Mark Dras Erik\u00a0D Reichle Simon\u00a0G Hosking Christopher Best Deborah Richards and Michael\u00a0J Richardson. 2022. Conversation dynamics in a multiplayer video game with knowledge asymmetry. Frontiers in Psychology 13 (2022) 1\u201316. 10.3389\/fpsyg.2022.1039431","DOI":"10.3389\/fpsyg.2022.1039431"},{"key":"e_1_3_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1145\/3462204.3481777"},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3719160.3736614"},{"key":"e_1_3_3_3_62_2","doi-asserted-by":"publisher","DOI":"10.1145\/634067.634189"},{"key":"e_1_3_3_3_63_2","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard\u00a0S","year":"2018","unstructured":"Richard\u00a0S Sutton and Andrew\u00a0G Barto. 2018. Reinforcement learning: An introduction. MIT press, Cambridge, MA, USA."},{"key":"e_1_3_3_3_64_2","unstructured":"DeepMind Interactive\u00a0Agents Team Josh Abramson Arun Ahuja Arthur Brussee Federico Carnevale Mary Cassin Felix Fischer Petko Georgiev Alex Goldin Mansi Gupta Tim Harley Felix Hill Peter\u00a0C Humphreys Alden Hung Jessica Landon Timothy Lillicrap Hamza Merzic Alistair Muldal Adam Santoro Guy Scully Tamara von Glehn Greg Wayne Nathaniel Wong Chen Yan and Rui Zhu. 2022. Creating Multimodal Interactive Agents with Imitation and Self-Supervised Learning. arxiv:https:\/\/arXiv.org\/abs\/2112.03763\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2112.03763"},{"key":"e_1_3_3_3_65_2","doi-asserted-by":"publisher","unstructured":"Indrani\u00a0Medhi Thies Nandita Menon Sneha Magapu Manisha Subramony and Jacki O\u2019Neill. 2017. How do you want your chatbot? An exploratory Wizard-of-Oz study with young Urban Indians. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) 10513 LNCS (2017) 441\u2013459. 10.1007\/978-3-319-67744-628\/TABLES\/1","DOI":"10.1007\/978-3-319-67744-628\/TABLES\/1"},{"key":"e_1_3_3_3_66_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. https:\/\/arxiv.org\/abs\/2302.13971v1"},{"key":"e_1_3_3_3_67_2","unstructured":"Jen tse Huang Eric\u00a0John Li Man\u00a0Ho Lam Tian Liang Wenxuan Wang Youliang Yuan Wenxiang Jiao Xing Wang Zhaopeng Tu and Michael\u00a0R. Lyu. 2025. How Far Are We on the Decision-Making of LLMs? Evaluating LLMs\u2019 Gaming Ability in Multi-Agent Environments. arxiv:https:\/\/arXiv.org\/abs\/2403.11807\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2403.11807"},{"key":"e_1_3_3_3_68_2","volume-title":"Advances in Neural Information Processing Systems","author":"Van\u00a0Seijen Harm","year":"2017","unstructured":"Harm Van\u00a0Seijen, Mehdi Fatemi, Joshua Romoff, Romain Laroche, Tavian Barnes, and Jeffrey Tsang. 2017. Hybrid Reward Architecture for Reinforcement Learning. In Advances in Neural Information Processing Systems , I.\u00a0Guyon, U.\u00a0Von Luxburg, S.\u00a0Bengio, H.\u00a0Wallach, R.\u00a0Fergus, S.\u00a0Vishwanathan, and R.\u00a0Garnett (Eds.), Vol.\u00a030. Curran Associates, Inc., Red Hook, NY, USA. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2017\/file\/1264a061d82a2edae1574b07249800d6-Paper.pdf"},{"key":"e_1_3_3_3_69_2","doi-asserted-by":"publisher","DOI":"10.5555\/3295222.3295349"},{"key":"e_1_3_3_3_70_2","doi-asserted-by":"publisher","unstructured":"Matthias W\u00f6lfel Christian\u00a0Felix Purps and Noah Percifull. 2022. Enabling Embodied Conversational Agents to\u00a0Respond to\u00a0Nonverbal Behavior of\u00a0the\u00a0Communication Partner. Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics) 13304 LNCS (2022) 591\u2013604. 10.1007\/978-3-031-05412-940\/FIGURES\/5","DOI":"10.1007\/978-3-031-05412-940\/FIGURES\/5"},{"key":"e_1_3_3_3_71_2","doi-asserted-by":"publisher","unstructured":"Xinli Xu Shaocong Dong Tingfa Xu Lihe Ding Jie Wang Peng Jiang Liqiang Song and Jianan Li. 2023. FusionRCNN: LiDAR-Camera Fusion for Two-Stage 3D Object Detection. Remote Sensing 15 7 (2023) 1839. 10.3390\/rs15071839","DOI":"10.3390\/rs15071839"},{"key":"e_1_3_3_3_72_2","unstructured":"Zhengyuan Yang Linjie Li Jianfeng Wang Kevin Lin Ehsan Azarnasab Faisal Ahmed Zicheng Liu Ce Liu Michael Zeng and Lijuan Wang. 2023. Mm-react: Prompting chatgpt for multimodal reasoning and action."},{"key":"e_1_3_3_3_73_2","first-page":"11809","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of Thoughts: Deliberate Problem Solving with Large Language Models. In Advances in Neural Information Processing Systems , A.\u00a0Oh, T.\u00a0Naumann, A.\u00a0Globerson, K.\u00a0Saenko, M.\u00a0Hardt, and S.\u00a0Levine (Eds.), Vol.\u00a036. Curran Associates, Inc., San Diego, CA, USA, 11809\u201311822. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/271db9922b8d1f4dd7aaef84ed5ac703-Paper-Conference.pdf"},{"key":"e_1_3_3_3_74_2","doi-asserted-by":"publisher","unstructured":"Ceyao Zhang Kaijie Yang Siyi Hu Zihao Wang Guanghe Li Yihang Sun Cheng Zhang Zhaowei Zhang Anji Liu Song\u00a0Chun Zhu Xiaojun Chang Junge Zhang Feng Yin Yitao Liang and Yaodong Yang. 2024. ProAgent: Building Proactive Cooperative Agents with Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence 38 (3 2024) 17591\u201317599. Issue 16. 10.1609\/AAAI.V38I16.29710","DOI":"10.1609\/AAAI.V38I16.29710"}],"event":{"name":"ICMI '25: International Conference on Multimodal Interaction","location":"Canberra Australia","acronym":"ICMI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 27th International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3716553.3750799","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T22:26:35Z","timestamp":1769466395000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3716553.3750799"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,12]]},"references-count":73,"alternative-id":["10.1145\/3716553.3750799","10.1145\/3716553"],"URL":"https:\/\/doi.org\/10.1145\/3716553.3750799","relation":{},"subject":[],"published":{"date-parts":[[2025,10,12]]},"assertion":[{"value":"2025-10-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}