{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T04:38:29Z","timestamp":1780375109576,"version":"3.54.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFE0203100"],"award-info":[{"award-number":["2024YFE0203100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476293"],"award-info":[{"award-number":["62476293"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["GJHZ20220913142600001"],"award-info":[{"award-number":["GJHZ20220913142600001"]}]},{"name":"Nansha Key R&D Program","award":["2022ZD014"],"award-info":[{"award-number":["2022ZD014"]}]},{"name":"General Embodied AI Center of Sun Yat-sen University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/tpami.2025.3554559","type":"journal-article","created":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:28:13Z","timestamp":1742974093000},"page":"5945-5957","source":"Crossref","is-referenced-by-count":35,"title":["NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8763-9530","authenticated-orcid":false,"given":"Bingqian","family":"Lin","sequence":"first","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9717-2308","authenticated-orcid":false,"given":"Yunshuang","family":"Nie","sequence":"additional","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5350-7805","authenticated-orcid":false,"given":"Ziming","family":"Wei","sequence":"additional","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5126-3460","authenticated-orcid":false,"given":"Jiaqi","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Pok Fu Lam, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1635-7893","authenticated-orcid":false,"given":"Shikui","family":"Ma","sequence":"additional","affiliation":[{"name":"Dataa Robotics Company, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Han","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3645-8972","authenticated-orcid":false,"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-8807","authenticated-orcid":false,"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3213-3062","authenticated-orcid":false,"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01282"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref7","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref8","article-title":"LLaMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref9","article-title":"Do as i can and not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022"},{"key":"ref10","article-title":"Inner monologue: Embodied reasoning through planning with language models","author":"Huang","year":"2022"},{"key":"ref11","article-title":"PaLM-E: An embodied multimodal language model","author":"Driess","year":"2023"},{"key":"ref12","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref13","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10611565"},{"key":"ref16","article-title":"GPT-4 technical report","author":"Achiam","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/3072.003.0014"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1012933107"},{"key":"ref19","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref20","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref22","first-page":"3318","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fried"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00679"},{"key":"ref26","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma"},{"key":"ref27","first-page":"20660","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Deng"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref30","first-page":"5834","article-title":"History aware multimodal transformer for vision-and-language navigation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01498"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref34","first-page":"5763","article-title":"Bevbert: Topo-metric map pre-training for language-guided navigation","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"An"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref38","article-title":"React: Synergizing reasoning and acting in language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao"},{"key":"ref39","first-page":"492","article-title":"Lm-nav: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. 6th Conf. Robot Learn.","author":"Shah"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29858"},{"key":"ref41","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023"},{"key":"ref42","article-title":"EmbodiedGPT: Vision-language pre-training via embodied chain of thought","author":"Mu","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_2"},{"key":"ref44","first-page":"2165","article-title":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Zitkovich"},{"key":"ref45","article-title":"Self-consistency improves chain of thought reasoning in language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref46","article-title":"Least-to-most prompting enables complex reasoning in large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou"},{"key":"ref47","first-page":"15476","article-title":"STaR: Self-taught reasoner bootstrapping reasoning with reasoning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zelikman"},{"key":"ref48","article-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao","year":"2023"},{"key":"ref49","article-title":"Large language model guided tree-of-thought","author":"Long","year":"2023"},{"key":"ref50","article-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref51","article-title":"LLaMA-adapter V2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3034494"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref54","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref55","article-title":"General evaluation for instruction conditioned navigation using dynamic time warping","volume-title":"Proc. Visually Grounded Interaction Lang., NeurIPS Workshop","author":"Ilharco"},{"key":"ref56","article-title":"Introducing chatgpt","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11026037\/10938647.pdf?arnumber=10938647","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,6]],"date-time":"2025-06-06T17:42:22Z","timestamp":1749231742000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10938647\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":56,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3554559","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}