{"id":"https://openalex.org/W4408841099","doi":"https://doi.org/10.1109/tpami.2025.3554559","title":"NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning","display_name":"NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning","publication_year":2025,"publication_date":"2025-03-26","ids":{"openalex":"https://openalex.org/W4408841099","doi":"https://doi.org/10.1109/tpami.2025.3554559","pmid":"https://pubmed.ncbi.nlm.nih.gov/40131754"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3554559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3554559","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101923104","display_name":"Bingqian Lin","orcid":"https://orcid.org/0000-0002-8763-9530"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Bingqian Lin","raw_affiliation_strings":["Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8763-9530","affiliations":[{"raw_affiliation_string":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053967353","display_name":"Yunshuang Nie","orcid":"https://orcid.org/0009-0000-9717-2308"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunshuang Nie","raw_affiliation_strings":["Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-9717-2308","affiliations":[{"raw_affiliation_string":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103119777","display_name":"Ziming Wei","orcid":"https://orcid.org/0009-0008-5350-7805"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ziming Wei","raw_affiliation_strings":["Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0008-5350-7805","affiliations":[{"raw_affiliation_string":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100434210","display_name":"Jiaqi Chen","orcid":"https://orcid.org/0009-0002-5126-3460"},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jiaqi Chen","raw_affiliation_strings":["University of Hong Kong, Pok Fu Lam, Hong Kong","University of Hong Kong"],"raw_orcid":"https://orcid.org/0009-0002-5126-3460","affiliations":[{"raw_affiliation_string":"University of Hong Kong, Pok Fu Lam, Hong Kong","institution_ids":["https://openalex.org/I889458895"]},{"raw_affiliation_string":"University of Hong Kong","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shikui Ma","orcid":"https://orcid.org/0009-0005-1635-7893"},"institutions":[{"id":"https://openalex.org/I4210159052","display_name":"Quanta Computer (China)","ror":"https://ror.org/05ta4fp83","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210159052"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shikui Ma","raw_affiliation_strings":["Dataa Robotics Company, Beijing, China","Dataa Robotics company"],"raw_orcid":"https://orcid.org/0009-0005-1635-7893","affiliations":[{"raw_affiliation_string":"Dataa Robotics Company, Beijing, China","institution_ids":["https://openalex.org/I4210159052"]},{"raw_affiliation_string":"Dataa Robotics company","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100297958","display_name":"Jianhua Han","orcid":null},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I4210159102","display_name":"Huawei Technologies (Sweden)","ror":"https://ror.org/0500fyd17","country_code":"SE","type":"company","lineage":["https://openalex.org/I2250955327","https://openalex.org/I4210159102"]}],"countries":["CN","SE"],"is_corresponding":false,"raw_author_name":"Jianhua Han","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shanghai, China","Huawei Noah's Ark Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Huawei Noah's Ark Lab","institution_ids":["https://openalex.org/I4210159102"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041457457","display_name":"Hang Xu","orcid":"https://orcid.org/0000-0003-3645-8972"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]},{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hang Xu","raw_affiliation_strings":["Huawei Noah's Ark Lab, Shanghai, China","Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3645-8972","affiliations":[{"raw_affiliation_string":"Huawei Noah's Ark Lab, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]},{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034967388","display_name":"Xiaojun Chang","orcid":"https://orcid.org/0000-0002-7778-8807"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaojun Chang","raw_affiliation_strings":["School of Information Science and Technology, University of Science and Technology of China, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-7778-8807","affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047878798","display_name":"Xiaodan Liang","orcid":"https://orcid.org/0000-0003-3213-3062"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodan Liang","raw_affiliation_strings":["Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","Shenzhen Campus of Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0003-3213-3062","affiliations":[{"raw_affiliation_string":"Shenzhen Campus, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]},{"raw_affiliation_string":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5101923104"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":59.5286,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.99880511,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"47","issue":"7","first_page":"5945","last_page":"5957"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9776999950408936,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9732000231742859,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.82793128490448},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7353742718696594},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6996966600418091},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43712037801742554},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35928115248680115},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3372272253036499}],"concepts":[{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.82793128490448},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7353742718696594},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6996966600418091},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43712037801742554},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35928115248680115},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3372272253036499}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3554559","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3554559","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40131754","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40131754","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.5400000214576721,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G6630003392","display_name":null,"funder_award_id":"62476293","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2084092936","https://openalex.org/W2926977875","https://openalex.org/W2951973805","https://openalex.org/W2963800628","https://openalex.org/W2964935470","https://openalex.org/W2979727876","https://openalex.org/W3034500398","https://openalex.org/W3034578524","https://openalex.org/W3096612875","https://openalex.org/W3100923070","https://openalex.org/W3106806814","https://openalex.org/W3107069568","https://openalex.org/W3165915253","https://openalex.org/W3172675210","https://openalex.org/W3195026654","https://openalex.org/W4226052928","https://openalex.org/W4238430855","https://openalex.org/W4312938887","https://openalex.org/W4385473486","https://openalex.org/W4390873167","https://openalex.org/W4393154152","https://openalex.org/W4393160097","https://openalex.org/W4401417232","https://openalex.org/W4402684154","https://openalex.org/W4402703032","https://openalex.org/W4402951641","https://openalex.org/W6751885507","https://openalex.org/W6757724268","https://openalex.org/W6770783600","https://openalex.org/W6778883912","https://openalex.org/W6780451406","https://openalex.org/W6791353385","https://openalex.org/W6803039797","https://openalex.org/W6809646742","https://openalex.org/W6810162553","https://openalex.org/W6811013733","https://openalex.org/W6837989031","https://openalex.org/W6839459284","https://openalex.org/W6839928859","https://openalex.org/W6846254642","https://openalex.org/W6849177959","https://openalex.org/W6850503672","https://openalex.org/W6850625674","https://openalex.org/W6851948999","https://openalex.org/W6852489829","https://openalex.org/W6852712537","https://openalex.org/W6852884379","https://openalex.org/W6853313673","https://openalex.org/W6853465110","https://openalex.org/W6854866820"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407"],"abstract_inverted_index":{"Vision-and-Language":[0],"Navigation":[1],"(VLN),":[2],"as":[3,119],"a":[4,72,92,100,120,229],"crucial":[5],"research":[6,26],"problem":[7],"of":[8,32,95,214],"Embodied":[9],"AI,":[10],"requires":[11],"an":[12,51],"embodied":[13,253],"agent":[14],"to":[15,85,91,111,123,129,181],"navigate":[16],"through":[17],"complex":[18],"3D":[19],"environments":[20],"following":[21],"natural":[22],"language":[23,34],"instructions.":[24],"Recent":[25],"has":[27],"highlighted":[28],"the":[29,61,65,96,107,113,125,130,134,141,146,150,153,159,168,177,190,211,217,238],"promising":[30],"capacity":[31],"large":[33],"models":[35],"(LLMs)":[36],"in":[37,50,99],"VLN":[38,62,201],"by":[39],"improving":[40,189],"navigational":[41,88,114],"reasoning":[42,151],"accuracy":[43],"and":[44,64,143,184,199,250],"interpretability.":[45],"However,":[46],"their":[47],"predominant":[48],"use":[49],"offline":[52],"manner":[53],"usually":[54],"suffers":[55],"from":[56,152,167],"substantial":[57],"domain":[58,97],"gap":[59,98],"between":[60],"task":[63],"LLM":[66,108,178],"training":[67,84,197],"corpus.":[68],"This":[69],"paper":[70],"proposes":[71],"novel":[73],"strategy":[74],"called":[75],"Navigational":[76],"Chain-of-Thought":[77],"(NavCoT),":[78],"where":[79],"we":[80],"fulfill":[81],"parameter-efficient":[82,224],"in-domain":[83],"enable":[86],"self-guided":[87],"decision,":[89],"leading":[90],"significant":[93,212],"mitigation":[94],"cost-effective":[101],"manner.":[102],"Specifically,":[103],"at":[104],"each":[105],"timestep,":[106],"is":[109],"prompted":[110],"forecast":[112],"chain-of-thought":[115,186],"by:":[116],"1)":[117],"acting":[118],"world":[121],"model":[122],"imagine":[124],"next":[126],"observation":[127,136],"according":[128],"instruction,":[131],"2)":[132],"selecting":[133],"candidate":[135],"that":[137,243],"best":[138],"aligns":[139],"with":[140,233],"imagination,":[142],"3)":[144],"determining":[145],"action":[147,160,191,219],"based":[148],"on":[149,237],"prior":[154],"steps.":[155],"In":[156],"this":[157],"way,":[158],"prediction":[161,220],"can":[162,179],"be":[163],"effectively":[164],"simplified":[165],"benefiting":[166],"disentangled":[169],"reasoning.":[170],"Through":[171,222],"constructing":[172],"formalized":[173],"labels":[174],"for":[175,188,258],"training,":[176],"learn":[180],"generate":[182],"desired":[183],"reasonable":[185],"outputs":[187],"decision.":[192],"Experimental":[193],"results":[194],"across":[195],"various":[196],"settings":[198],"popular":[200],"benchmarks":[202],"(e.g.,":[203],"Room-to-Room":[204],"(R2R),":[205],"Room-across-Room":[206],"(RxR),":[207],"Room-for-Room":[208],"(R4R))":[209],"show":[210],"superiority":[213],"NavCoT":[215,227,244],"over":[216],"direct":[218],"variants.":[221],"simple":[223],"finetuning,":[225],"our":[226],"outperforms":[228],"recent":[230],"GPT4-based":[231],"approach":[232],"$\\sim$\u223c7%":[234],"relative":[235],"improvement":[236],"R2R":[239],"dataset.":[240],"We":[241],"believe":[242],"will":[245],"help":[246],"unlock":[247],"more":[248],"task-adaptive":[249],"scalable":[251],"LLM-based":[252],"agents,":[254],"which":[255],"are":[256],"helpful":[257],"developing":[259],"real-world":[260],"robotics":[261],"applications.":[262]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":18}],"updated_date":"2026-05-28T09:10:13.091523","created_date":"2025-10-10T00:00:00"}