{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T07:22:52Z","timestamp":1781335372180,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T00:00:00Z","timestamp":1745539200000},"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":[[2025,4,26]]},"DOI":"10.1145\/3706598.3713760","type":"proceedings-article","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T04:24:56Z","timestamp":1745468696000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":29,"title":["Proactive Conversational Agents with Inner Thoughts"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6988-5471","authenticated-orcid":false,"given":"Xingyu Bruce","family":"Liu","sequence":"first","affiliation":[{"name":"HCI Research, UCLA, Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1401-8482","authenticated-orcid":false,"given":"Shitao","family":"Fang","sequence":"additional","affiliation":[{"name":"Interactive Intelligent Systems Laboratory, The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0850-5831","authenticated-orcid":false,"given":"Weiyan","family":"Shi","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, Massachusetts, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5598-5324","authenticated-orcid":false,"given":"Chien-Sheng","family":"Wu","sequence":"additional","affiliation":[{"name":"Salesforce AI, Palo Alto, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5495-6441","authenticated-orcid":false,"given":"Takeo","family":"Igarashi","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8527-1744","authenticated-orcid":false,"given":"Xiang 'Anthony'","family":"Chen","sequence":"additional","affiliation":[{"name":"HCI Research, UCLA, Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"e_1_3_3_3_2_2","doi-asserted-by":"crossref","unstructured":"James\u00a0E Allen Curry\u00a0I Guinn and Eric Horvtz. 1999. Mixed-initiative interaction. IEEE Intelligent Systems and their Applications 14 5 (1999) 14\u201323.","DOI":"10.1109\/5254.796083"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/3196709.3196734"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3272973.3272990"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"crossref","unstructured":"Christoph Bartneck Dana Kuli\u0107 Elizabeth Croft and Susana Zoghbi. 2009. Measurement instruments for the anthropomorphism animacy likeability perceived intelligence and perceived safety of robots. International journal of social robotics 1 (2009) 71\u201381.","DOI":"10.1007\/s12369-008-0001-3"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1037\/11164-000"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3471158.3472232"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.3115\/1708376.1708411"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.3115\/1708376.1708409"},{"key":"e_1_3_3_3_10_2","first-page":"98","volume-title":"Proceedings of the SIGDIAL 2011 Conference","author":"Bohus Dan","year":"2011","unstructured":"Dan Bohus and Eric Horvitz. 2011. Multiparty turn taking in situated dialog: Study, lessons, and directions. In Proceedings of the SIGDIAL 2011 Conference. 98\u2013109."},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"crossref","unstructured":"Simone Borsci Alessio Malizia Martin Schmettow Frank Van Der\u00a0Velde Gunay Tariverdiyeva Divyaa Balaji and Alan Chamberlain. 2022. The chatbot usability scale: the design and pilot of a usability scale for interaction with AI-based conversational agents. Personal and ubiquitous computing 26 (2022) 95\u2013119.","DOI":"10.1007\/s00779-021-01582-9"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"crossref","unstructured":"Paul\u00a0T Brady. 1968. A statistical analysis of on-off patterns in 16 conversations. Bell System Technical Journal 47 1 (1968) 73\u201391.","DOI":"10.1002\/j.1538-7305.1968.tb00031.x"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"crossref","unstructured":"Virginia Braun and Victoria Clarke. 2006. Using thematic analysis in psychology. Qualitative research in psychology 3 2 (2006) 77\u2013101.","DOI":"10.1191\/1478088706qp063oa"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511813085"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"crossref","unstructured":"Shuo-yiin Chang Bo Li Tara\u00a0N Sainath Chao Zhang Trevor Strohman Qiao Liang and Yanzhang He. 2022. Turn-taking prediction for natural conversational speech. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2208.13321 (2022).","DOI":"10.21437\/Interspeech.2022-566"},{"key":"e_1_3_3_3_16_2","unstructured":"Maira\u00a0Gatti de Bayser Paulo Cavalin Claudio Pinhanez and Bianca Zadrozny. 2019. Learning multi-party turn-taking models from dialogue logs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1907.02090 (2019)."},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Yang Deng Wenqiang Lei Wai Lam and Tat-Seng Chua. 2023. A survey on proactive dialogue systems: Problems methods and prospects. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.02750 (2023).","DOI":"10.24963\/ijcai.2023\/738"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Starkey Duncan. 1972. Some signals and rules for taking speaking turns in conversations. Journal of personality and social psychology 23 2 (1972) 283.","DOI":"10.1037\/h0033031"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Starkey Duncan\u00a0Jr and George Niederehe. 1974. On signalling that it\u2019s your turn to speak. Journal of experimental social psychology 10 3 (1974) 234\u2013247.","DOI":"10.1016\/0022-1031(74)90070-5"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"crossref","unstructured":"Paul Ekman and Wallace\u00a0V Friesen. 1969. The repertoire of nonverbal behavior: Categories origins usage and coding. semiotica 1 1 (1969) 49\u201398.","DOI":"10.1515\/semi.1969.1.1.49"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Erik Ekstedt and Gabriel Skantze. 2020. Turngpt: a transformer-based language model for predicting turn-taking in spoken dialog. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2010.10874 (2020).","DOI":"10.18653\/v1\/2020.findings-emnlp.268"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"crossref","unstructured":"Jonathan St\u00a0BT Evans. 2008. Dual-processing accounts of reasoning judgment and social cognition. Annu. Rev. Psychol. 59 1 (2008) 255\u2013278.","DOI":"10.1146\/annurev.psych.59.103006.093629"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"crossref","unstructured":"Cecilia\u00a0E Ford and Sandra\u00a0A Thompson. 1996. Interactional units in conversation: Syntactic intonational and pragmatic resources for the management of turns. Studies in interactional sociolinguistics 13 (1996) 134\u2013184.","DOI":"10.1017\/CBO9780511620874.003"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835533"},{"key":"e_1_3_3_3_25_2","volume-title":"Interaction Ritual: Essays on Face-to-Face Behavior","author":"Goffman Erving","year":"1967","unstructured":"Erving Goffman. 1967. Interaction Ritual: Essays on Face-to-Face Behavior. Doubleday."},{"key":"e_1_3_3_3_26_2","first-page":"41","volume-title":"Syntax and semantics","author":"Grice H.\u00a0P.","year":"1975","unstructured":"H.\u00a0P. Grice. 1975. Logic and conversation. In Syntax and semantics. Vol.\u00a03. Academic Press, 41\u201358."},{"key":"e_1_3_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/1124772.1124961"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.3115\/116580.116613"},{"key":"e_1_3_3_3_29_2","volume-title":"Contextual design: defining customer-centered systems","author":"Holtzblatt Karen","year":"1997","unstructured":"Karen Holtzblatt and Hugh Beyer. 1997. Contextual design: defining customer-centered systems. Elsevier."},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/302979.303030"},{"key":"e_1_3_3_3_31_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 preprint arXiv:https:\/\/arXiv.org\/abs\/2106.09685 (2021)."},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/2663204.2663271"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.81"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.sigdial-1.17"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268943"},{"key":"e_1_3_3_3_36_2","volume-title":"The Soar cognitive architecture","author":"Laird John\u00a0E","year":"2019","unstructured":"John\u00a0E Laird. 2019. The Soar cognitive architecture. MIT press."},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3594250"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581566"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"crossref","unstructured":"Yang Liu Dan Iter Yichong Xu Shuohang Wang Ruochen Xu and Chenguang Zhu. 2023. G-eval: Nlg evaluation using gpt-4 with better human alignment. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2303.16634 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.153"},{"key":"e_1_3_3_3_40_2","unstructured":"Zeming Liu Haifeng Wang Zheng-Yu Niu Hua Wu Wanxiang Che and Ting Liu. 2020. Towards conversational recommendation over multi-type dialogs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2005.03954 (2020)."},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"crossref","unstructured":"John\u00a0K Local John Kelly and William\u00a0HG Wells. 1986. Towards a phonology of conversation: turn-taking in Tyneside English1. Journal of Linguistics 22 2 (1986) 411\u2013437.","DOI":"10.1017\/S0022226700010859"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"crossref","unstructured":"David\u00a0H McFarland. 2001. Respiratory markers of conversational interaction. (2001).","DOI":"10.1044\/1092-4388(2001\/012)"},{"key":"e_1_3_3_3_43_2","first-page":"7721","volume-title":"International conference on machine learning","author":"Miller John\u00a0P","year":"2021","unstructured":"John\u00a0P Miller, Rohan Taori, Aditi Raghunathan, Shiori Sagawa, Pang\u00a0Wei Koh, Vaishaal Shankar, Percy Liang, Yair Carmon, and Ludwig Schmidt. 2021. Accuracy on the line: on the strong correlation between out-of-distribution and in-distribution generalization. In International conference on machine learning. PMLR, 7721\u20137735."},{"key":"e_1_3_3_3_44_2","unstructured":"OpenAI. 2024. Learning to Reason with LLMs. (September 2024). https:\/\/openai.com\/index\/learning-to-reason-with-llms\/"},{"key":"e_1_3_3_3_45_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"e_1_3_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1007\/11550617_19"},{"key":"e_1_3_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1007\/11550617_20"},{"key":"e_1_3_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462839"},{"key":"e_1_3_3_3_49_2","first-page":"487","volume-title":"The Proceedings of the First International Conference on the Practical Application of Intelligent Agents and Multi Agent Technology","volume":"1","author":"Rhodes Bradley","year":"1996","unstructured":"Bradley Rhodes and Thad Starner. 1996. Remembrance Agent: A Continuously Running Automated Information Retrieval System. In The Proceedings of the First International Conference on the Practical Application of Intelligent Agents and Multi Agent Technology , Vol.\u00a01. ACM, 487\u2013495."},{"key":"e_1_3_3_3_50_2","doi-asserted-by":"crossref","unstructured":"Frank\u00a0E Ritter Farnaz Tehranchi and Jacob\u00a0D Oury. 2019. ACT-R: A cognitive architecture for modeling cognition. Wiley Interdisciplinary Reviews: Cognitive Science 10 3 (2019) e1488.","DOI":"10.1002\/wcs.1488"},{"key":"e_1_3_3_3_51_2","doi-asserted-by":"crossref","unstructured":"Sonia Roccas Lilach Sagiv Shalom\u00a0H Schwartz and Ariel Knafo. 2002. The big five personality factors and personal values. Personality and social psychology bulletin 28 6 (2002) 789\u2013801.","DOI":"10.1177\/0146167202289008"},{"key":"e_1_3_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.4324\/9781315080932"},{"key":"e_1_3_3_3_53_2","doi-asserted-by":"crossref","unstructured":"Harvey Sacks Emanuel\u00a0A Schegloff and Gail Jefferson. 1974. A simplest systematics for the organization of turn-taking for conversation. language 50 4 (1974) 696\u2013735.","DOI":"10.1353\/lan.1974.0010"},{"key":"e_1_3_3_3_54_2","volume-title":"LREC","author":"Shaikh Samira","year":"2010","unstructured":"Samira Shaikh, Tomek Strzalkowski, George\u00a0Aaron Broadwell, Jennifer Stromer-Galley, Sarah\u00a0M Taylor, and Nick Webb. 2010. MPC: A Multi-Party Chat Corpus for Modeling Social Phenomena in Discourse.. In LREC. Citeseer."},{"key":"e_1_3_3_3_55_2","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 36 (2024)."},{"key":"e_1_3_3_3_56_2","doi-asserted-by":"crossref","unstructured":"Gabriel Skantze. 2021. Turn-taking in conversational systems and human-robot interaction: a review. Computer Speech & Language 67 (2021) 101178.","DOI":"10.1016\/j.csl.2020.101178"},{"key":"e_1_3_3_3_57_2","doi-asserted-by":"publisher","DOI":"10.5555\/38407"},{"key":"e_1_3_3_3_58_2","doi-asserted-by":"crossref","unstructured":"Jianheng Tang Tiancheng Zhao Chenyan Xiong Xiaodan Liang Eric\u00a0P Xing and Zhiting Hu. 2019. Target-guided open-domain conversation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1905.11553 (2019).","DOI":"10.18653\/v1\/P19-1565"},{"key":"e_1_3_3_3_59_2","doi-asserted-by":"crossref","unstructured":"Louis Ten\u00a0Bosch Nelleke Oostdijk and Lou Boves. 2005. On temporal aspects of turn taking in conversational dialogues. Speech Communication 47 1-2 (2005) 80\u201386.","DOI":"10.1016\/j.specom.2005.05.009"},{"key":"e_1_3_3_3_60_2","unstructured":"Naftali Tishby Fernando\u00a0C Pereira and William Bialek. 2000. The information bottleneck method. arXiv preprint physics\/0004057 (2000)."},{"key":"e_1_3_3_3_61_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2007.sigdial-1.15"},{"key":"e_1_3_3_3_62_2","unstructured":"Marilyn Walker and Steve Whittaker. 1995. Mixed initiative in dialogue: An investigation into discourse segmentation. arXiv preprint cmp-lg\/9504007 (1995)."},{"key":"e_1_3_3_3_63_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445645"},{"key":"e_1_3_3_3_64_2","unstructured":"Jimmy Wei Kurt Shuster Arthur Szlam Jason Weston Jack Urbanek and Mojtaba Komeili. 2023. Multi-party chat: Conversational agents in group settings with humans and models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.13835 (2023)."},{"key":"e_1_3_3_3_65_2","unstructured":"Jason Wei Xuezhi Wang Dale Schuurmans Maarten Bosma Fei Xia Ed Chi Quoc\u00a0V Le Denny Zhou et\u00a0al. 2022. Chain-of-thought prompting elicits reasoning in large language models. Advances in neural information processing systems 35 (2022) 24824\u201324837."},{"key":"e_1_3_3_3_66_2","doi-asserted-by":"publisher","unstructured":"Joseph Weizenbaum. 1966. ELIZA\u2014a Computer Program for the Study of Natural Language Communication between Man and Machine. Commun. ACM 9 1 (jan 1966) 36\u201345. 10.1145\/365153.365168","DOI":"10.1145\/365153.365168"},{"key":"e_1_3_3_3_67_2","doi-asserted-by":"publisher","DOI":"10.1145\/958160.958187"},{"key":"e_1_3_3_3_68_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.166"},{"key":"e_1_3_3_3_69_2","first-page":"852","volume-title":"Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation","author":"Yamashita Sanae","year":"2023","unstructured":"Sanae Yamashita, Koji Inoue, Ao Guo, Shota Mochizuki, Tatsuya Kawahara, and Ryuichiro Higashinaka. 2023. Realpersonachat: A realistic persona chat corpus with interlocutors\u2019 own personalities. In Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation. 852\u2013861."},{"key":"e_1_3_3_3_70_2","unstructured":"Shunyu Yao Dian Yu Jeffrey Zhao Izhak Shafran Tom Griffiths Yuan Cao and Karthik Narasimhan. 2024. Tree of thoughts: Deliberate problem solving with large language models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_3_71_2","unstructured":"Shunyu Yao Jeffrey Zhao Dian Yu Nan Du Izhak Shafran Karthik Narasimhan and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.03629 (2022)."},{"key":"e_1_3_3_3_72_2","doi-asserted-by":"crossref","unstructured":"Saizheng Zhang. 2018. Personalizing dialogue agents: I have a dog do you have pets too. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1801.07243 (2018).","DOI":"10.18653\/v1\/P18-1205"}],"event":{"name":"CHI 2025: CHI Conference on Human Factors in Computing Systems","location":"Yokohama Japan","acronym":"CHI '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3713760","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3706598.3713760","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T05:21:14Z","timestamp":1751606474000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3706598.3713760"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,25]]},"references-count":71,"alternative-id":["10.1145\/3706598.3713760","10.1145\/3706598"],"URL":"https:\/\/doi.org\/10.1145\/3706598.3713760","relation":{},"subject":[],"published":{"date-parts":[[2025,4,25]]},"assertion":[{"value":"2025-04-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}