{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:17:30Z","timestamp":1783455450969,"version":"3.55.0"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62506231"],"award-info":[{"award-number":["62506231"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62372482"],"award-info":[{"award-number":["62372482"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shanghai Commitee of Science and Technology, China","award":["24511103200"],"award-info":[{"award-number":["24511103200"]}]},{"name":"Scientific Research Innovation Capability Support Project for Young Faculty","award":["ZYGXQNJSKYCXNLZCXM"],"award-info":[{"award-number":["ZYGXQNJSKYCXNLZCXM"]}]},{"DOI":"10.13039\/501100012152","name":"National Postdoctoral Program for Innovative Talents","doi-asserted-by":"publisher","award":["BX20250379"],"award-info":[{"award-number":["BX20250379"]}],"id":[{"id":"10.13039\/501100012152","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2025M771521"],"award-info":[{"award-number":["2025M771521"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]},{"name":"General Embodied AI Center of Sun Yat-sen University"},{"name":"Shanghai Artificial Intelligence Laboratory through XPLORER PRIZE Grants"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3682514","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:45:30Z","timestamp":1775763930000},"page":"9782-9796","source":"Crossref","is-referenced-by-count":1,"title":["EvolveNav: Empowering LLM-Based Vision-Language Navigation via Self-Improving Embodied Reasoning"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8763-9530","authenticated-orcid":false,"given":"Bingqian","family":"Lin","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, 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"}]},{"given":"Khun Loun","family":"Zai","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\/0000-0003-0040-6177","authenticated-orcid":false,"given":"Mingfei","family":"Han","sequence":"additional","affiliation":[{"name":"Department of Computer Vision, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4619-9679","authenticated-orcid":false,"given":"Rongtao","family":"Xu","sequence":"additional","affiliation":[{"name":"Department of Computer Vision, Mohamed Bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minzhe","family":"Niu","sequence":"additional","affiliation":[{"name":"Yinwang Intelligent Technology Company, Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianhua","family":"Han","sequence":"additional","affiliation":[{"name":"Yinwang Intelligent Technology Company, Ltd., Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7374-8739","authenticated-orcid":false,"given":"Hanwang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4947-5619","authenticated-orcid":false,"given":"Bokui","family":"Chen","sequence":"additional","affiliation":[{"name":"Tsinghua Shenzhen International Graduate School, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1533-8576","authenticated-orcid":false,"given":"Cewu","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, 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.2019.00679"},{"key":"ref2","article-title":"Self-monitoring navigation agent via auxiliary progress estimation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ma","year":"2019"},{"key":"ref3","first-page":"20660","article-title":"Evolving graphical planner: Contextual global planning for vision-and-language navigation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Deng","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58607-2_18"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01003"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1159"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00750"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1268"},{"key":"ref9","first-page":"3318","article-title":"Speaker-follower models for vision-and-language navigation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Fried","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00167"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_5"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00169"},{"key":"ref13","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","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00168"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01604"},{"key":"ref16","first-page":"15418","article-title":"HOP: History-and-order aware pre-training for vision-and-language navigation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qiao","year":"2022"},{"key":"ref17","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Brown","year":"2020"},{"key":"ref18","article-title":"LLAMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref19","article-title":"LLAMA 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref20","first-page":"287","article-title":"Do as I can and not as I say: Grounding language in robotic affordances","volume-title":"Proc. Conf. Robot Learn.","author":"Ahn"},{"key":"ref21","first-page":"1769","article-title":"Inner monologue: Embodied reasoning through planning with language models","volume-title":"Proc. Conf. Robot Learn.","author":"Huang"},{"key":"ref22","first-page":"8469","article-title":"PALM-E: An embodied multimodal language model","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Driess","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.529"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28597"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611565"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01315"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.079"},{"key":"ref28","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv:2303.08774.2"},{"key":"ref29","article-title":"Vicuna","year":"2023"},{"key":"ref30","first-page":"3157","article-title":"Robotic control via embodied chain-of-thought reasoning","volume-title":"Proc. Conf. Robot Learn.","author":"Zawalski"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00166"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3554559"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref34","first-page":"394","article-title":"Vision-and-dialog navigation","volume-title":"Proc. Conf. Robot Learn.","author":"Thomason","year":"2019"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01000"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01250"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1181"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.356"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00166"},{"key":"ref40","article-title":"BevBERT: Topo-metric map pre-training for language-guided navigation","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"An","year":"2023"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01103"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3407759"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_15"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01444"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01293"},{"key":"ref46","first-page":"2998","article-title":"LLM-planner: Few-shot grounded planning for embodied agents with large language models","volume-title":"Proc. Int. Conf. Comput. Vis.","author":"Hee","year":"2023"},{"key":"ref47","article-title":"ReAct: Synergizing reasoning and acting in language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yao","year":"2023"},{"key":"ref48","first-page":"492","article-title":"LM-NAV: Robotic navigation with large pre-trained models of language, vision, and action","volume-title":"Proc. Conf. Robot Learn.","author":"Shah","year":"2022"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29858"},{"key":"ref50","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref51","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. Conf. Robot Learn.","author":"Huang"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/icaps.v34i1.31506"},{"key":"ref53","article-title":"Introducing chatGPT","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i22.34526"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02569"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref57","article-title":"Deepseek-V3 technical report","author":"Liu","year":"2024"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1090"},{"key":"ref59","article-title":"SpatialCoT: Advancing spatial reasoning through coordinate alignment and chain-of-thought for embodied task planning","author":"Liu","year":"2025"},{"key":"ref60","article-title":"Tag2Text: Guiding vision-language model via image tagging","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2024"},{"key":"ref61","article-title":"SpaCy: Industrial-strength natural language processing in python","author":"Honnibal","year":"2020"},{"key":"ref62","first-page":"15418","article-title":"HOP: History-and-order aware pre-training for vision-and-language navigation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Qiao","year":"2022"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00646"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01040"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01416"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_25"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01432"},{"key":"ref68","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref69","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","year":"2023"},{"key":"ref70","article-title":"LLaVA-NeXT: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00179"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_7"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2025.XXI.018"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11478375.pdf?arnumber=11478375","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:44:28Z","timestamp":1783453468000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11478375\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":73,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3682514","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":[[2026,8]]}}}