{"id":"https://openalex.org/W7128511961","doi":"https://doi.org/10.48550/arxiv.2602.07055","title":"Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?","display_name":"Theory of Space: Can Foundation Models Construct Spatial Beliefs through Active Exploration?","publication_year":2026,"publication_date":"2026-02-04","ids":{"openalex":"https://openalex.org/W7128511961","doi":"https://doi.org/10.48550/arxiv.2602.07055"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.07055","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046257318","display_name":"Pingyue Zhang","orcid":"https://orcid.org/0000-0002-5884-632X"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhang, Pingyue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125564936","display_name":"Zihan Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zihan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125570612","display_name":"Yue Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yue","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125499420","display_name":"Jieyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jieyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123548031","display_name":"Letian Xue","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xue, Letian","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125531984","display_name":"Zihan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zihan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114245169","display_name":"Qineng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Qineng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125567434","display_name":"Keshigeyan Chandrasegaran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chandrasegaran, Keshigeyan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125522375","display_name":"Ruohan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Ruohan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125554526","display_name":"Yejin Choi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Choi, Yejin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125485704","display_name":"Ranjay Krishna","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishna, Ranjay","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125526388","display_name":"Jiajun Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jiajun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125508732","display_name":"Li Fei-Fei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei-Fei, Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125482159","display_name":"Manling Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Manling","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":14,"corresponding_author_ids":["https://openalex.org/A5046257318"],"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":0.21279999613761902,"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":0.21279999613761902,"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":0.1695999950170517,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/T11883","display_name":"Embodied and Extended Cognition","score":0.10719999670982361,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6194000244140625},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5945000052452087},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5924999713897705},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.5062000155448914},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5026000142097473},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.41190001368522644},{"id":"https://openalex.org/keywords/complete-information","display_name":"Complete information","score":0.40720000863075256},{"id":"https://openalex.org/keywords/belief-revision","display_name":"Belief revision","score":0.40610000491142273}],"concepts":[{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6194000244140625},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5972999930381775},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5945000052452087},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5924999713897705},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131999850273132},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5062000155448914},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5026000142097473},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.41190001368522644},{"id":"https://openalex.org/C113336015","wikidata":"https://www.wikidata.org/wiki/Q574010","display_name":"Complete information","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C128913409","wikidata":"https://www.wikidata.org/wiki/Q3566063","display_name":"Belief revision","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.37389999628067017},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3580000102519989},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.351500004529953},{"id":"https://openalex.org/C170494330","wikidata":"https://www.wikidata.org/wiki/Q1778434","display_name":"Cognitive map","level":3,"score":0.3458999991416931},{"id":"https://openalex.org/C2777371692","wikidata":"https://www.wikidata.org/wiki/Q2178611","display_name":"Spatial cognition","level":3,"score":0.3391000032424927},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31360000371932983},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C519536355","wikidata":"https://www.wikidata.org/wiki/Q21021151","display_name":"Repurposing","level":2,"score":0.2858999967575073},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26919999718666077},{"id":"https://openalex.org/C52622258","wikidata":"https://www.wikidata.org/wiki/Q131222","display_name":"Information theory","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2558000087738037}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.07055","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.07055","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.07055","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":"article"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.07055","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"publisher-specific-oa","license_id":"https://openalex.org/licenses/publisher-specific-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.5197824239730835,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Spatial":[0],"embodied":[1],"intelligence":[2],"requires":[3],"agents":[4,117,171,186],"to":[5,7,39,48,72,88,132,156,173,202],"act":[6],"acquire":[8,41],"information":[9,42],"under":[10],"partial":[11,58],"observability.":[12],"While":[13],"multimodal":[14],"foundation":[15,199],"models":[16,87,101,128,200],"excel":[17],"at":[18,94],"passive":[19],"perception,":[20],"their":[21,90],"capacity":[22],"for":[23],"active,":[24],"self-directed":[25],"exploration":[26,46,71],"remains":[27],"understudied.":[28],"We":[29,60],"propose":[30],"Theory":[31],"of":[32,99],"Space,":[33],"defined":[34],"as":[35,127],"an":[36,74,109,144],"agent's":[37],"ability":[38],"actively":[40],"through":[43,63],"self-directed,":[44],"active":[45,209],"and":[47,51],"construct,":[49],"revise,":[50],"exploit":[52],"a":[53,64,162],"spatial":[54,82,92,154,206],"belief":[55,83,136,164],"from":[56,150],"sequential,":[57],"observations.":[59],"evaluate":[61],"this":[62],"benchmark":[65],"where":[66,112,170],"the":[67],"goal":[68],"is":[69,81,143,182,188],"curiosity-driven":[70],"build":[73],"accurate":[75],"cognitive":[76],"map.":[77],"A":[78],"key":[79],"innovation":[80],"probing,":[84,137],"which":[85],"prompts":[86],"reveal":[89],"internal":[91],"representations":[93],"each":[95],"step.":[96],"Our":[97,194],"evaluation":[98],"state-of-the-art":[100],"reveals":[102],"several":[103],"critical":[104],"bottlenecks.":[105],"First,":[106],"we":[107,123,138,166],"identify":[108],"Active-Passive":[110],"Gap,":[111],"performance":[113],"drops":[114],"significantly":[115],"when":[116],"must":[118],"autonomously":[119],"gather":[120],"information.":[121],"Second,":[122],"find":[124],"high":[125],"inefficiency,":[126],"explore":[129],"unsystematically":[130],"compared":[131],"program-based":[133],"proxies.":[134],"Through":[135],"diagnose":[139],"that":[140,152,197],"while":[141],"perception":[142],"initial":[145],"bottleneck,":[146],"global":[147],"beliefs":[148,207],"suffer":[149],"instability":[151],"causes":[153],"knowledge":[155],"degrade":[157],"over":[158],"time.":[159],"Finally,":[160],"using":[161],"false":[163],"paradigm,":[165],"uncover":[167],"Belief":[168],"Inertia,":[169],"fail":[172],"update":[174],"obsolete":[175],"priors":[176],"with":[177],"new":[178],"evidence.":[179],"This":[180],"issue":[181],"present":[183],"in":[184,191],"text-based":[185],"but":[187],"particularly":[189],"severe":[190],"vision-based":[192],"models.":[193],"findings":[195],"suggest":[196],"current":[198],"struggle":[201],"maintain":[203],"coherent,":[204],"revisable":[205],"during":[208],"exploration.":[210]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-02-11T00:00:00"}