{"id":"https://openalex.org/W7214901952","doi":"https://doi.org/10.48550/arxiv.2609.37353","title":"Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation","display_name":"Seek Before You Move: Evidence Seeking for Progress Grounding in Vision-Language Navigation","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214901952","doi":"https://doi.org/10.48550/arxiv.2609.37353"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37353","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37353","pdf_url":"https://arxiv.org/pdf/2609.37353","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37353","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153638783","display_name":"Zhimin Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhimin","raw_affiliation_strings":["Pengcheng Laboratory","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153637187","display_name":"Meiyuan Zhu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhu, Meiyuan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153677705","display_name":"Duo Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Duo","raw_affiliation_strings":["Pengcheng Laboratory","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001399798","display_name":"Linjia Kang","orcid":"https://orcid.org/0009-0008-2971-7087","observed_orcids":["https://orcid.org/0009-0008-2971-7087"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kang, Linjia","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143862339","display_name":"Yajun Wang","orcid":"https://orcid.org/0000-0001-6828-0545","observed_orcids":["https://orcid.org/0000-0001-6828-0545"]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yajun","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)","International Digital Economy Academy","Pengcheng Laboratory","South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"International Digital Economy Academy","institution_ids":[]},{"raw_affiliation_string":"Pengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153572706","display_name":"Yuan Ni","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ni, Yuan","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd. , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd. , Shenzhen , China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153613996","display_name":"Xiaohang Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4401726822","display_name":"Ping An (China)","ror":"https://ror.org/004yv2z91","country_code":"CN","type":"company","lineage":["https://openalex.org/I4401726822"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Xiaohang","raw_affiliation_strings":["Ping An Technology (Shenzhen) Co., Ltd. , Shenzhen , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Ping An Technology (Shenzhen) Co., Ltd. , Shenzhen , China","institution_ids":["https://openalex.org/I4401726822"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103836866","display_name":"Tianlu Pan","orcid":"https://orcid.org/0009-0009-2020-4397","observed_orcids":["https://orcid.org/0009-0009-2020-4397"]},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan, Tianlu","raw_affiliation_strings":["Pengcheng Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153571685","display_name":"Jingyan Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Jingyan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153612712","display_name":"Yaowei Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I204983213","display_name":"Harbin Institute of Technology","ror":"https://ror.org/01yqg2h08","country_code":"CN","type":"education","lineage":["https://openalex.org/I204983213"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yaowei","raw_affiliation_strings":["Harbin Institute of Technology (Shenzhen)","International Digital Economy Academy","Pengcheng Laboratory","South China University of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology (Shenzhen)","institution_ids":["https://openalex.org/I204983213"]},{"raw_affiliation_string":"International Digital Economy Academy","institution_ids":[]},{"raw_affiliation_string":"Pengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"South China University of Technology","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153606482","display_name":"Zhi Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhi","raw_affiliation_strings":["Pengcheng Laboratory","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pengcheng Laboratory","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5634999871253967,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5634999871253967,"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":0.3118000030517578,"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/T11904","display_name":"Spatial Cognition and Navigation","score":0.03750000149011612,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-and-language-navigation","display_name":"vision-and-language navigation","score":0.9959999918937683},{"id":"https://openalex.org/keywords/egocentric-vision","display_name":"egocentric vision","score":0.7260000109672546},{"id":"https://openalex.org/keywords/robot-navigation","display_name":"robot navigation","score":0.3799999952316284}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.843999981880188},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6119999885559082},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5913000106811523},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5041000247001648},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.42660000920295715},{"id":"https://openalex.org/C2777877512","wikidata":"https://www.wikidata.org/wiki/Q1116097","display_name":"Common ground","level":2,"score":0.39500001072883606},{"id":"https://openalex.org/C71889745","wikidata":"https://www.wikidata.org/wiki/Q1783264","display_name":"Counterfactual conditional","level":3,"score":0.39410001039505005},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.3896999955177307},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.36550000309944153},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.3447999954223633},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.323199987411499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30709999799728394},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2847999930381775},{"id":"https://openalex.org/C166052673","wikidata":"https://www.wikidata.org/wiki/Q83021","display_name":"Empirical evidence","level":2,"score":0.2784999907016754},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2671999931335449},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.26420000195503235},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2587999999523163},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25609999895095825}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37353","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37353","pdf_url":"https://arxiv.org/pdf/2609.37353","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.37353","doi":"https://doi.org/10.48550/arxiv.2609.37353","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37353","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.37353","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37353","pdf_url":"https://arxiv.org/pdf/2609.37353","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214901952.pdf","grobid_xml":"https://content.openalex.org/works/W7214901952.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2736601468","https://openalex.org/W2929928372","https://openalex.org/W2964339842","https://openalex.org/W3100923070","https://openalex.org/W4311001206","https://openalex.org/W4386185600","https://openalex.org/W4399759187","https://openalex.org/W4402353981","https://openalex.org/W4415016638","https://openalex.org/W4415087308","https://openalex.org/W4415316236","https://openalex.org/W4417008141","https://openalex.org/W7134916114","https://openalex.org/W7155060173","https://openalex.org/W7162094295","https://openalex.org/W7220847659"],"related_works":["https://openalex.org/W4417008141","https://openalex.org/W7221510544","https://openalex.org/W4416665646","https://openalex.org/W3106641651","https://openalex.org/W2962744691","https://openalex.org/W7167251701","https://openalex.org/W2909303996","https://openalex.org/W7221529448","https://openalex.org/W7215129353","https://openalex.org/W7213505171"],"abstract_inverted_index":{"Vision-Language":[0],"Navigation":[1],"(VLN)":[2],"requires":[3],"agents":[4,20],"to":[5,73,119,189,192],"continuously":[6],"ground":[7],"task":[8],"progress":[9,76,96,142,238],"from":[10,180],"long-horizon":[11],"instructions":[12],"and":[13,27,45,78,127,141,215,223,228],"partial":[14],"egocentric":[15],"observations.":[16,103],"Existing":[17],"VLM-based":[18],"navigation":[19,198],"typically":[21],"reason":[22],"only":[23],"over":[24,217],"available":[25],"observations":[26],"may":[28,41],"remain":[29],"confident":[30],"even":[31,48],"when":[32],"task-relevant":[33,102],"evidence":[34,128,139],"is":[35,105],"missing.":[36],"For":[37],"example,":[38],"an":[39,90],"agent":[40,71],"confidently":[42],"proceed":[43],"forward":[44],"get":[46],"lost":[47],"though":[49],"the":[50,53,70,181,218],"landmark":[51],"indicating":[52],"next":[54],"turn":[55],"lies":[56],"outside":[57],"its":[58],"current":[59],"field":[60],"of":[61,101],"view.":[62],"We":[63,159],"term":[64],"this":[65],"failure":[66],"mode":[67],"Progress":[68],"Myopia:":[69],"fails":[72],"recognize":[74],"unreliable":[75],"grounding":[77],"continues":[79],"acting":[80],"on":[81,132,196,201,221],"insufficient":[82],"evidence.":[83],"To":[84],"address":[85],"it,":[86],"we":[87],"propose":[88],"SeekVLN,":[89],"evidence-seeking":[91,173,233],"framework":[92],"that":[93,205],"couples":[94],"semantic":[95],"reasoning":[97,143],"with":[98,124,175],"active":[99],"acquisition":[100],"SeekVLN":[104,206],"trained":[106],"in":[107],"two":[108],"stages:":[109],"First,":[110],"Future-guided":[111],"Reverse":[112],"Generation":[113],"(FRG)":[114],"uses":[115,185],"future":[116],"expert":[117,122,146],"actions":[118],"augment":[120],"offline":[121],"trajectories":[123,134],"supplementary":[125],"views":[126],"annotations.":[129],"Supervised":[130],"fine-tuning":[131],"these":[133],"establishes":[135],"a":[136,176,186],"prior":[137],"for":[138,167,235],"seeking":[140,155,193],"without":[144],"additional":[145],"interaction.":[147],"However,":[148],"imitation":[149],"alone":[150],"does":[151],"not":[152],"reveal":[153],"whether":[154],"improves":[156],"subsequent":[157,197],"navigation.":[158],"therefore":[160],"introduce":[161],"Counterfactual":[162],"Contrastive":[163],"Policy":[164],"Optimization":[165],"(C2PO)":[166],"reinforcement":[168],"fine-tuning.":[169],"By":[170],"comparing":[171],"each":[172],"branch":[174,179],"counterfactual":[177],"direct-navigation":[178],"same":[182],"state,":[183],"C2PO":[184],"contrastive":[187],"reward":[188],"assign":[190],"credit":[191],"decisions":[194],"based":[195],"benefit.":[199],"Experiments":[200],"simulated":[202,227],"benchmarks":[203],"show":[204],"achieves":[207],"state-of-the-art":[208],"performance,":[209],"improving":[210],"success":[211],"rate":[212],"by":[213],"12.7%":[214],"7.5%":[216],"base":[219],"model":[220],"R2R-CE":[222],"RxR-CE,":[224],"respectively.":[225],"Both":[226],"real-world":[229],"evaluations":[230],"exhibit":[231],"human-like":[232],"behaviors":[234],"more":[236],"reliable":[237],"grounding.":[239]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}