{"id":"https://openalex.org/W7206217872","doi":"https://doi.org/10.48550/arxiv.2609.00920","title":"VerNav: Verifier-First Low-Latency Vision-and-Language Navigation","display_name":"VerNav: Verifier-First Low-Latency Vision-and-Language Navigation","publication_year":2026,"publication_date":"2026-09-01","ids":{"openalex":"https://openalex.org/W7206217872","doi":"https://doi.org/10.48550/arxiv.2609.00920"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.00920","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.00920","pdf_url":"https://arxiv.org/pdf/2609.00920","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2609.00920","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136130241","display_name":"Zhixin Wang","orcid":"https://orcid.org/0000-0003-2350-735X","observed_orcids":["https://orcid.org/0000-0003-2350-735X"]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhixin","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148906598","display_name":"Chengzheyi Yao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao, Chengzheyi","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149160917","display_name":"Leyuan Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Leyuan","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125202038","display_name":"Xiaosong Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Xiaosong","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5148917934","display_name":"Yongzhao Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Yongzhao","raw_affiliation_strings":["University of Electronic Science and Technology of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I150229711"],"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7300000190734863,"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":0.7300000190734863,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.1712999939918518,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.015399999916553497,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/vision-and-language-navigation","display_name":"vision-and-language navigation","score":0.9950000047683716},{"id":"https://openalex.org/keywords/low-latency-decision-making","display_name":"low-latency decision-making","score":0.7350000143051147},{"id":"https://openalex.org/keywords/reinforcement-fine-tuning","display_name":"reinforcement fine-tuning","score":0.9279999732971191},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.609000027179718}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7559999823570251},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.6733999848365784},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.6559000015258789},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5418000221252441},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47540000081062317},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.45840001106262207},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.4440000057220459},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.4133000075817108},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.4032000005245209},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.3873000144958496},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.3370000123977661},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2782999873161316}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.00920","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.00920","pdf_url":"https://arxiv.org/pdf/2609.00920","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.00920","doi":"https://doi.org/10.48550/arxiv.2609.00920","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.00920","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.00920","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.00920","pdf_url":"https://arxiv.org/pdf/2609.00920","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/W7206217872.pdf","grobid_xml":"https://content.openalex.org/works/W7206217872.grobid-xml"},"referenced_works_count":17,"referenced_works":["https://openalex.org/W2964339842","https://openalex.org/W3168867926","https://openalex.org/W4311001206","https://openalex.org/W4318718936","https://openalex.org/W4390873167","https://openalex.org/W4393154152","https://openalex.org/W4401042755","https://openalex.org/W4408841099","https://openalex.org/W4414281281","https://openalex.org/W4414987633","https://openalex.org/W4415036464","https://openalex.org/W4415087308","https://openalex.org/W4415336575","https://openalex.org/W4417008141","https://openalex.org/W7133208539","https://openalex.org/W7133340007","https://openalex.org/W7138299395"],"related_works":["https://openalex.org/W7125807736","https://openalex.org/W7214721891","https://openalex.org/W7138299395","https://openalex.org/W7123355754","https://openalex.org/W7130308819","https://openalex.org/W4408841099","https://openalex.org/W7077973791","https://openalex.org/W4411949569","https://openalex.org/W7138845225","https://openalex.org/W7164854364"],"abstract_inverted_index":{"Vision-and-Language":[0],"Navigation":[1],"(VLN)":[2],"requires":[3],"an":[4,63],"agent":[5],"to":[6,13,73],"navigate":[7],"through":[8],"unseen":[9],"3D":[10],"environments":[11],"according":[12],"natural-language":[14],"instructions.":[15],"Explicit":[16],"reasoning":[17],"can":[18],"improve":[19,80],"instruction":[20],"understanding":[21],"and":[22,102],"semantic":[23],"grounding,":[24],"but":[25],"autoregressive":[26,56,156],"generation":[27,57],"at":[28],"every":[29],"step":[30,149],"accumulates":[31],"large":[32],"decision-stage":[33,51,145],"latency":[34,52,147],"over":[35,111],"multi-step":[36,112],"navigation.":[37],"We":[38],"propose":[39],"VerNav,":[40],"a":[41,88],"verifier-first":[42],"framework":[43],"for":[44,70],"low-latency":[45],"LLM-based":[46,139],"VLN.":[47],"The":[48],"verifier":[49,100],"reduces":[50],"by":[53,150],"replacing":[54],"per-step":[55],"with":[58,83,155],"batched":[59],"action":[60],"verification,":[61],"while":[62,142],"entropy-based":[64],"adaptive":[65],"generator":[66],"is":[67],"invoked":[68],"only":[69],"uncertain":[71],"decisions":[72],"produce":[74],"compact":[75],"state":[76],"evidence.":[77],"To":[78],"further":[79],"navigation":[81,113,135],"performance":[82,136],"the":[84,121,127],"verifier,":[85],"we":[86],"introduce":[87],"two-stage":[89],"alignment":[90,97],"scheme:":[91],"(i)":[92],"VPO":[93],"improves":[94],"local":[95],"action-preference":[96],"in":[98],"static":[99],"training,":[101],"(ii)":[103],"step-level":[104],"reinforcement":[105],"fine-tuning":[106],"provides":[107],"dense":[108],"progress":[109],"rewards":[110],"rollouts":[114],"during":[115],"dynamic":[116],"task":[117],"execution.":[118],"Experiments":[119],"on":[120],"Room-to-Room":[122],"(R2R)":[123],"benchmark":[124],"show":[125],"that":[126],"verifier-only":[128],"decision":[129],"path":[130],"of":[131],"VerNav":[132],"achieves":[133],"competitive":[134],"among":[137],"representative":[138],"VLN":[140],"agents":[141],"reducing":[143],"average":[144],"LLM":[146],"per":[148],"more":[151],"than":[152],"$10\\times$":[153],"compared":[154],"methods.":[157]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-03T00:00:00"}
