{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T20:55:55Z","timestamp":1774558555885,"version":"3.50.1"},"reference-count":39,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001711","name":"Swiss National Science Foundation","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100001711","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Centre of Competence in Digital Fabrication"},{"name":"Huawei Tech R&D"},{"name":"ETH RobotX research grant"},{"DOI":"10.13039\/501100012652","name":"ETH Zürich Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012652","id-type":"DOI","asserted-by":"publisher"}]},{"name":"ETH AI Center"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/lra.2026.3669804","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T20:54:17Z","timestamp":1772571257000},"page":"5606-5613","source":"Crossref","is-referenced-by-count":0,"title":["A Pragmatist Robot: Learning to Plan Tasks by Experiencing the Real World"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4998-5576","authenticated-orcid":false,"given":"Kaixian","family":"Qu","sequence":"first","affiliation":[{"name":"Robotic Systems Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0534-1025","authenticated-orcid":false,"given":"Guowei","family":"Lan","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2773-9369","authenticated-orcid":false,"given":"Ren\u00e9","family":"Zurbr\u00fcgg","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-2926-5419","authenticated-orcid":false,"given":"Changan","family":"Chen","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3929-9391","authenticated-orcid":false,"given":"Christopher E.","family":"Mower","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6083-6171","authenticated-orcid":false,"given":"Haitham","family":"Bou-Ammar","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, London, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4285-4990","authenticated-orcid":false,"given":"Marco","family":"Hutter","sequence":"additional","affiliation":[{"name":"Robotic Systems Lab, ETH Zürich, Zürich, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Evaluating large language models trained on code","author":"Chen","year":"2021"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.eacl-srw.17"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.452"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160591"},{"key":"ref6","first-page":"287","article-title":"Do as I can, not as I say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn.","author":"Ahn","year":"2023"},{"key":"ref7","article-title":"ROS-LLM: A ROS framework for embodied AI with task feedback and structured reasoning","author":"Mower","year":"2024"},{"key":"ref8","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Proc. Conf. Robot Learn.","author":"Huang","year":"2023"},{"key":"ref9","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. Conf. Robot Learn.","author":"Huang","year":"2023"},{"key":"ref10","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref11","article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","author":"Bubeck","year":"2023"},{"key":"ref12","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024"},{"key":"ref13","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Brohan","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11127975"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3471457"},{"key":"ref16","article-title":"Look before you leap: Unveiling the power of GPT-4V in robotic vision-language planning","author":"Hu","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0377"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610455"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2024.1455375"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128444"},{"key":"ref21","first-page":"3468","article-title":"REFLECT: Summarizing robot experiences for failure explanation and correction","volume-title":"Proc. Conf. Robot Learn.","author":"Liu","year":"2023"},{"key":"ref22","first-page":"1863","article-title":"I can tell what I am doing: Toward real-world natural language grounding of robot experiences","volume-title":"Proc. Conf. Robot Learn.","author":"Wang","year":"2025"},{"key":"ref23","article-title":"Creative robot tool use with large language models","author":"Xu","year":"2023"},{"key":"ref24","article-title":"RAP: Retrieval-augmented planning with contextual memory for multimodal LLM agents","volume-title":"Proc. NeurIPS Workshop Open-World Agents","author":"Kagaya","year":"2024"},{"key":"ref25","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V","author":"Yang","year":"2023"},{"key":"ref26","first-page":"37321","article-title":"PIVOT: Iterative visual prompting elicits actionable knowledge for VLMs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Nasiriany","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.062"},{"key":"ref28","first-page":"3304","article-title":"Towards open-world grasping with large vision-language models","volume-title":"Proc. Conf. Robot Learn.","author":"Tziafas","year":"2025"},{"key":"ref29","first-page":"3568","article-title":"ThinkGrasp: A vision-language system for strategic part grasping in clutter","volume-title":"Proc. Conf. Robot Learn.","author":"Qian","year":"2025"},{"key":"ref30","article-title":"Grounded SAM: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/83.623193"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/sii.2019.8700380"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7758092"},{"key":"ref37","article-title":"New embedding models and API updates","year":"2024"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00638"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.320"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11435997\/11419794.pdf?arnumber=11419794","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:51:51Z","timestamp":1774554711000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11419794\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":39,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3669804","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}