{"id":"https://openalex.org/W7155178111","doi":"https://doi.org/10.48550/arxiv.2604.19064","title":"The Essence of Balance for Self-Improving Agents in Vision-and-Language Navigation","display_name":"The Essence of Balance for Self-Improving Agents in Vision-and-Language Navigation","publication_year":2026,"publication_date":"2026-04-21","ids":{"openalex":"https://openalex.org/W7155178111","doi":"https://doi.org/10.48550/arxiv.2604.19064"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.19064","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19064","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.19064","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134354332","display_name":"Zhen Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Zhen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134312145","display_name":"Yuhan Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134341137","display_name":"Jinjun Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Jinjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134346517","display_name":"Jianyi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Jianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134355683","display_name":"Wei Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134357879","display_name":"Jingwen Fu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fu, Jingwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8216999769210815,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.8216999769210815,"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/T10914","display_name":"Tactile and Sensory Interactions","score":0.029500000178813934,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.016699999570846558,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/balance","display_name":"Balance (ability)","score":0.711899995803833},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6858000159263611},{"id":"https://openalex.org/keywords/diversity","display_name":"Diversity (politics)","score":0.5907999873161316},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5842999815940857},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4860000014305115},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.37560001015663147}],"concepts":[{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.711899995803833},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6858000159263611},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.5907999873161316},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5856999754905701},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5842999815940857},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4860000014305115},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4652999937534332},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.37560001015663147},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.3246000111103058},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3174000084400177},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.3084999918937683},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3075000047683716},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C48677424","wikidata":"https://www.wikidata.org/wiki/Q6888088","display_name":"Mode (computer interface)","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.19064","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19064","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.19064","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.19064","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"vision-and-language":[1],"navigation":[2],"(VLN),":[3],"self-improvement":[4,65,81,137],"from":[5,159,165],"policy-induced":[6,49],"experience,":[7],"using":[8],"only":[9],"standard":[10],"VLN":[11],"action":[12,44],"supervision,":[13],"critically":[14],"depends":[15],"on":[16,143,153],"balancing":[17],"behavioral":[18,37,92],"diversity":[19,38,134],"and":[20,59,103,109,135,146,163],"learning":[21,32,50],"stability,":[22],"which":[23],"governs":[24],"whether":[25],"the":[26,99],"agent":[27],"can":[28,47],"extract":[29],"a":[30,76],"reliable":[31,64],"signal":[33],"for":[34,79,151],"improvement.":[35],"Increasing":[36],"is":[39],"necessary":[40],"to":[41,111,161,167],"expose":[42],"alternative":[43],"hypotheses":[45,93],"but":[46],"destabilize":[48],"signals,":[51],"whereas":[52],"overly":[53],"conservative":[54],"stability":[55],"constraints":[56],"suppress":[57],"exploration":[58],"induce":[60],"early":[61],"commitment,":[62],"making":[63],"difficult.":[66],"To":[67],"address":[68],"this":[69],"challenge,":[70],"we":[71],"propose":[72],"Stability-Diversity":[73],"Balance":[74],"(SDB),":[75],"plug-and-play":[77],"mechanism":[78],"balanced":[80],"in":[82,98],"VLN.":[83],"SDB":[84,156],"expands":[85],"each":[86],"decision":[87],"step":[88],"into":[89],"multiple":[90],"latent":[91],"by":[94],"applying":[95],"controlled":[96],"shifts":[97],"instruction-conditioned":[100],"hidden":[101],"states,":[102],"then":[104],"performs":[105],"reliability-aware":[106],"soft":[107],"evaluation":[108],"aggregation":[110],"retain":[112],"diverse":[113],"yet":[114],"instruction-consistent":[115],"alternatives":[116],"during":[117],"learning.":[118],"An":[119],"explicit":[120],"regularizer":[121],"further":[122],"constrains":[123],"hypothesis":[124,133],"interactions,":[125],"preventing":[126],"excessive":[127],"drift":[128],"or":[129],"premature":[130],"collapse":[131],"of":[132],"stabilizing":[136],"without":[138],"discarding":[139],"training":[140],"signals.":[141],"Experiments":[142],"R2R,":[144],"SOON,":[145],"REVERIE":[147,154],"show":[148],"consistent":[149],"improvements;":[150],"example,":[152],"val-unseen,":[155],"improves":[157],"SPL":[158],"33.73":[160],"35.93":[162],"OSR":[164],"51.07":[166],"54.25.":[168]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-23T00:00:00"}
