{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T16:45:05Z","timestamp":1779295505313,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T00:00:00Z","timestamp":1756080000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,8,25]]},"DOI":"10.1109\/ro-man63969.2025.11217646","type":"proceedings-article","created":{"date-parts":[[2025,11,3]],"date-time":"2025-11-03T18:42:29Z","timestamp":1762195349000},"page":"931-938","source":"Crossref","is-referenced-by-count":4,"title":["Agreeing to Interact in Human-Robot Interaction using Large Language Models and Vision Language Models"],"prefix":"10.1109","author":[{"given":"Kazuhiro","family":"Sasabuchi","sequence":"first","affiliation":[{"name":"Microsoft,Applied Robotics Research,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoki","family":"Wake","sequence":"additional","affiliation":[{"name":"Microsoft,Applied Robotics Research,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsushi","family":"Kanehira","sequence":"additional","affiliation":[{"name":"Microsoft,Applied Robotics Research,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Takamatsu","sequence":"additional","affiliation":[{"name":"Microsoft,Applied Robotics Research,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Katsushi","family":"Ikeuchi","sequence":"additional","affiliation":[{"name":"Microsoft,Applied Robotics Research,Redmond,WA,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3173386.3173390"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2218523120"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.artint.2005.03.005"},{"key":"ref4","first-page":"637","article-title":"Directions robot: in-the-wild experiences and lessons learned","volume-title":"Proceedings of the 2014 international conference on Autonomous agents and multi-agent systems","author":"Bohus"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s12369-015-0298-7"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ROMAN.2018.8525514"},{"key":"ref7","first-page":"1350","article-title":"Temporal models for robot classification of human interruptibility","volume-title":"Proceedings of the 16th Conference on Autonomous Agents and MultiAgent Systems","author":"Banerjee"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4325"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5527"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-024-40231-1"},{"key":"ref11","article-title":"Understanding social reasoning in language models with language models","volume":"36","author":"Gandhi","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.699"},{"key":"ref13","article-title":"Kokomind: Can large language models understand social interactions?","author":"Shi","year":"2023"},{"key":"ref14","article-title":"Bias in emotion recognition with chatgpt","author":"Wake","year":"2023"},{"key":"ref15","first-page":"371","article-title":"Understanding large-language model (llm)-powered human-robot interaction","volume-title":"Proceedings of the 2024 ACM\/IEEE International Conference on Human-Robot Interaction","author":"Kim"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3651029"},{"key":"ref17","article-title":"Developing social robots with empathetic non-verbal cues using large language models","author":"Lee","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3610978.3640767"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-024-00550-5"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3477090"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025765"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1111\/j.1468-2885.1999.tb00355.x"},{"key":"ref23","article-title":"The semantics of dialogue acts","volume-title":"Proceedings of the Ninth International Conference on Computational Semantics (IWCS 2011)","author":"Bunt"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/2598510.2598513"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2013.IX.055"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-92611-2_4"},{"issue":"2","key":"ref27","first-page":"95","article-title":"A benchmark of facial recognition pipelines and co-usability performances of modules","volume-title":"Journal of Information Technologies","volume":"17","author":"Serengil","year":"2024"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378180"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.352"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3025105"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126386"},{"key":"ref32","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"}],"event":{"name":"2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","location":"Eindhoven, Netherlands","start":{"date-parts":[[2025,8,25]]},"end":{"date-parts":[[2025,8,29]]}},"container-title":["2025 34th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11217544\/11217526\/11217646.pdf?arnumber=11217646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T06:00:29Z","timestamp":1762236029000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11217646\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/ro-man63969.2025.11217646","relation":{},"subject":[],"published":{"date-parts":[[2025,8,25]]}}}