{"id":"https://openalex.org/W7214740201","doi":"https://doi.org/10.48550/arxiv.2609.35032","title":"JRDB-AVR: An Active Visual Reasoning Benchmark for Embodied Agents in Real-World Environments","display_name":"JRDB-AVR: An Active Visual Reasoning Benchmark for Embodied Agents in Real-World Environments","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214740201","doi":"https://doi.org/10.48550/arxiv.2609.35032"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.35032","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35032","pdf_url":"https://arxiv.org/pdf/2609.35032","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","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/2609.35032","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153423737","display_name":"Zhixi Cai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Cai, Zhixi","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088951276","display_name":"Fucai Ke","orcid":"https://orcid.org/0000-0001-9709-1305","observed_orcids":["https://orcid.org/0000-0001-9709-1305"]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ke, Fucai","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153550562","display_name":"Sukai Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Huang, Sukai","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083095334","display_name":"Mar\u00eda Garc\u00eda de la Banda","orcid":"https://orcid.org/0000-0002-6666-514X","observed_orcids":["https://orcid.org/0000-0002-6666-514X"]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"de la Banda, Maria Garcia","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064839018","display_name":"Peter J. Stuckey","orcid":"https://orcid.org/0000-0003-2186-0459","observed_orcids":["https://orcid.org/0000-0003-2186-0459"]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Stuckey, Peter J.","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081525024","display_name":"Gholamreza Haffari","orcid":"https://orcid.org/0000-0001-7326-8380","observed_orcids":["https://orcid.org/0000-0001-7326-8380"]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Haffari, Gholamreza","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034608678","display_name":"Hamid Rezatofighi","orcid":"https://orcid.org/0000-0002-8659-8773","observed_orcids":["https://orcid.org/0000-0002-8659-8773"]},"institutions":[{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Rezatofighi, Hamid","raw_affiliation_strings":["Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I56590836"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I56590836"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.9789999723434448,"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":0.9789999723434448,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.012900000438094139,"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"}},{"id":"https://openalex.org/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.002099999925121665,"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/vision-language-models","display_name":"vision-language models","score":0.6869999766349792},{"id":"https://openalex.org/keywords/evidence-grounding","display_name":"evidence grounding","score":0.4490000009536743},{"id":"https://openalex.org/keywords/question-generation","display_name":"question generation","score":0.5580000281333923},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.3140000104904175},{"id":"https://openalex.org/keywords/viewpoint-selection","display_name":"viewpoint selection","score":0.47999998927116394},{"id":"https://openalex.org/keywords/temporal-search","display_name":"temporal search","score":0.902999997138977},{"id":"https://openalex.org/keywords/compositional-reasoning","display_name":"compositional reasoning","score":0.9520000219345093},{"id":"https://openalex.org/keywords/world-models","display_name":"world models","score":0.5360000133514404}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.8148000240325928},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7228999733924866},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6917999982833862},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6150000095367432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6055999994277954},{"id":"https://openalex.org/C193611912","wikidata":"https://www.wikidata.org/wiki/Q4677596","display_name":"Active vision","level":2,"score":0.4250999987125397},{"id":"https://openalex.org/C113954288","wikidata":"https://www.wikidata.org/wiki/Q186885","display_name":"Timestamp","level":2,"score":0.4185999929904938},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.37770000100135803},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3675000071525574},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36149999499320984},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3596000075340271},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.33570000529289246},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.32749998569488525},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.3246999979019165},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.32030001282691956},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2867000102996826},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C77967617","wikidata":"https://www.wikidata.org/wiki/Q4677561","display_name":"Active learning (machine learning)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.25440001487731934}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.35032","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35032","pdf_url":"https://arxiv.org/pdf/2609.35032","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.35032","doi":"https://doi.org/10.48550/arxiv.2609.35032","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.35032","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:2609.35032","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.35032","pdf_url":"https://arxiv.org/pdf/2609.35032","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1995592097","display_name":null,"funder_award_id":"N62909","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"},{"id":"https://openalex.org/G4148687015","display_name":null,"funder_award_id":"FA8750-23-2-1016","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"}],"funders":[{"id":"https://openalex.org/F4320312169","display_name":"National Computational Infrastructure","ror":"https://ror.org/04yx6dh41"},{"id":"https://openalex.org/F4320320971","display_name":"Monash University","ror":"https://ror.org/02bfwt286"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"},{"id":"https://openalex.org/F4320338298","display_name":"Office of Naval Research Global","ror":"https://ror.org/00rk2pe57"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214740201.pdf","grobid_xml":"https://content.openalex.org/works/W7214740201.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W2893390896","https://openalex.org/W2963541336","https://openalex.org/W3144974485","https://openalex.org/W4318718936","https://openalex.org/W4366850747","https://openalex.org/W4385574156","https://openalex.org/W4387294612","https://openalex.org/W4388482547","https://openalex.org/W4389520747","https://openalex.org/W4390872747","https://openalex.org/W4403853618","https://openalex.org/W4404725708","https://openalex.org/W4407794264","https://openalex.org/W4409368309","https://openalex.org/W4412605375","https://openalex.org/W4413145669","https://openalex.org/W4413147823","https://openalex.org/W4414585765","https://openalex.org/W4414897598","https://openalex.org/W4415183921","https://openalex.org/W4416050967","https://openalex.org/W4416780398","https://openalex.org/W4417063342","https://openalex.org/W4417077984","https://openalex.org/W6910720181","https://openalex.org/W7077901839","https://openalex.org/W7127603244","https://openalex.org/W7133202489","https://openalex.org/W7138233761","https://openalex.org/W7138913573","https://openalex.org/W7155074923","https://openalex.org/W7168241717","https://openalex.org/W7169159688"],"related_works":["https://openalex.org/W7138233761","https://openalex.org/W4417324092","https://openalex.org/W7165025162","https://openalex.org/W4416288921","https://openalex.org/W7221044136","https://openalex.org/W4405173422","https://openalex.org/W4414742267","https://openalex.org/W7125208096","https://openalex.org/W4417456772","https://openalex.org/W6979312233"],"abstract_inverted_index":{"In":[0],"complex":[1],"embodied":[2,99,201],"visual":[3,54,104,126,202],"reasoning":[4,55,69,105,155],"scenarios,":[5],"an":[6,95,98,160],"agent":[7],"often":[8],"has":[9],"only":[10],"a":[11,22,38,76,86,103,152,172],"limited":[12],"field":[13],"of":[14],"view,":[15],"and":[16,30,61,70,112,115,123,144,166,178,193,205],"the":[17,44,120,124],"evidence":[18,71,127,179],"needed":[19],"to":[20],"answer":[21,40,122,176],"question":[23],"may":[24,35],"be":[25],"distributed":[26],"across":[27],"time,":[28,47],"viewpoint,":[29],"interacting":[31],"objects.":[32],"A":[33],"model":[34,165],"therefore":[36],"give":[37],"plausible":[39],"without":[41],"ever":[42],"observing":[43],"relevant":[45],"object,":[46],"or":[48],"view":[49],"that":[50,66,90,158,185,194],"supports":[51],"it.":[52,129],"Current":[53],"benchmarks":[56],"largely":[57],"evaluate":[58],"passive":[59],"observations":[60,109],"final":[62,121],"answers,":[63],"overlooking":[64],"settings":[65],"require":[67],"active":[68,154,195],"acquisition.":[72],"We":[73,148],"introduce":[74,150],"JRDB-AVR,":[75],"benchmark":[77,131,206],"derived":[78],"from":[79],"existing":[80],"real-world":[81,137],"JRDB":[82],"robotics":[83],"data":[84],"through":[85,168],"structured":[87],"question-generation":[88],"engine":[89],"turns":[91],"this":[92],"gap":[93,174],"into":[94],"explicit":[96,161],"evaluation:":[97],"agentic":[100,156],"system":[101],"receives":[102],"question,":[106],"requests":[107],"bounded":[108],"by":[110],"timestamp":[111],"viewing":[113],"angle,":[114],"is":[116,198],"evaluated":[117],"on":[118],"both":[119],"grounded":[125],"supporting":[128],"The":[130],"contains":[132],"diverse":[133],"questions":[134],"over":[135],"multiple":[136],"environments":[138],"involving":[139],"temporal":[140],"search,":[141],"viewpoint":[142],"selection,":[143],"human-oriented":[145],"compositional":[146],"reasoning.":[147,203],"also":[149],"JRDB-AVR-Agent,":[151],"reference":[153],"method":[157],"maintains":[159],"observation-grounded":[162],"graph-based":[163],"world":[164],"answers":[167,192],"solving.":[169],"Experiments":[170],"reveal":[171],"substantial":[173],"between":[175],"accuracy":[177,180],"in":[181],"current":[182,186],"baselines,":[183],"showing":[184],"VLMs":[187],"can":[188],"produce":[189],"unsupported":[190],"correct":[191],"evidence-aware":[196],"evaluation":[197],"necessary":[199],"for":[200],"Code":[204],"are":[207],"available":[208],"at":[209],"https://github.com/ControlNet/JRDB-AVR.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}
