{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,4]],"date-time":"2026-08-04T21:02:10Z","timestamp":1785877330153,"version":"3.56.0"},"reference-count":48,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"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":[[2024,5,13]]},"DOI":"10.1109\/icra57147.2024.10610855","type":"proceedings-article","created":{"date-parts":[[2024,8,8]],"date-time":"2024-08-08T17:51:05Z","timestamp":1723139465000},"page":"286-299","source":"Crossref","is-referenced-by-count":144,"title":["RoCo: Dialectic Multi-Robot Collaboration with Large Language Models"],"prefix":"10.1109","author":[{"given":"Zhao","family":"Mandi","sequence":"first","affiliation":[{"name":"Columbia University in the City of New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shreeya","family":"Jain","sequence":"additional","affiliation":[{"name":"Columbia University in the City of New York"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuran","family":"Song","sequence":"additional","affiliation":[{"name":"Columbia University in the City of New York"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.423"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.689"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611163"},{"key":"ref5","article-title":"MuJoCo Menagerie: A collection of high-quality simulation models for MuJoCo","author":"Contributors","year":"2022"},{"key":"ref6","article-title":"no, to the right\u201d\u2013online language corrections for robotic manipulation via shared autonomy","author":"Cui","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10161147"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342169"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2015.7354289"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7138999"},{"key":"ref11","article-title":"Palm-e: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref12","article-title":"Improving factuality and reasoning in language models through multiagent debate","author":"Du","year":"2023"},{"key":"ref13","article-title":"Learning a decentralized multi-arm motion planner","author":"Ha","year":"2020","journal-title":"Conference on Robotic Learning (CoRL)"},{"key":"ref14","article-title":"Instruct2act: Mapping multi-modality instructions to robotic actions with large language model","author":"Huang","year":"2023"},{"key":"ref15","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022","journal-title":"Conference on Robot Learning"},{"key":"ref16","article-title":"Ai safety via debate","author":"Irving","year":"2018"},{"key":"ref17","article-title":"Alphablock: Embodied finetuning for vision-language reasoning in robot manipulation","author":"Jin","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1177\/0278364911406761"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1994.351231"},{"key":"ref20","article-title":"Toward grounded social reasoning","author":"Kwon","year":"2023"},{"key":"ref21","article-title":"Reward design with language models","author":"Kwon","year":"2023"},{"key":"ref22","article-title":"Camel: Communicative agents for \u201dmind\" exploration of large scale language model society","author":"Li","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10160591"},{"key":"ref24","article-title":"Code as policis: Language model programs for embodied control","author":"Liang","year":"2022"},{"key":"ref25","article-title":"Encouraging divergent thinking in large language models through multi-agent debate","author":"Liang","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-023-10131-7"},{"key":"ref27","article-title":"Training socially aligned language models in simulated human society","author":"Liu","year":"2023"},{"key":"ref28","volume-title":"Introducing claude","year":"2023"},{"key":"ref29","article-title":"Interactive language: Talking to robots in real time","author":"Lynch","year":"2022"},{"key":"ref30","article-title":"Simple open-vocabulary object detection with vision transformers","author":"Minderer","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.clinicalnlp-1.12"},{"key":"ref32","article-title":"Gpt-4 technical report","year":"2023","journal-title":"ArXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606763"},{"key":"ref34","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.019"},{"key":"ref36","article-title":"Dialogue games for benchmarking language understanding: Motivation, taxonomy, strategy","author":"Schlangen","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/icra48891.2023.10161317"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2012.6386109"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.simpa.2020.100022"},{"key":"ref40","article-title":"Demo2code: From summarizing demonstrations to synthesizing code via extended chain-of-thought","author":"Wang","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341577"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2017.2708134"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.029"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/70.976030"},{"key":"ref45","article-title":"Language to rewards for robotic skill synthesis","author":"Yu","year":"2023"},{"key":"ref46","article-title":"Socratic models: Composing zero-shot multimodal reasoning with language","author":"Zeng","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812055"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342363"}],"event":{"name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","location":"Yokohama, Japan","start":{"date-parts":[[2024,5,13]]},"end":{"date-parts":[[2024,5,17]]}},"container-title":["2024 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10609961\/10609862\/10610855.pdf?arnumber=10610855","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,10]],"date-time":"2024-08-10T05:57:51Z","timestamp":1723269471000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10610855\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/icra57147.2024.10610855","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]}}}