{"id":"https://openalex.org/W7164030224","doi":"https://doi.org/10.48550/arxiv.2606.08952","title":"AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models","display_name":"AlloSpatial: Agentic Harness Framework for Spatial Reasoning in Foundation Models","publication_year":2026,"publication_date":"2026-06-08","ids":{"openalex":"https://openalex.org/W7164030224","doi":"https://doi.org/10.48550/arxiv.2606.08952"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.08952","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08952","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.2606.08952","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5048633696","display_name":"Shouwei Ruan","orcid":"https://orcid.org/0009-0007-0481-5855"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruan, Shouwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138201687","display_name":"Bin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138211134","display_name":"Zhenyu Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zhenyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138284217","display_name":"Qihui Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Qihui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138224751","display_name":"Yuxiang Zhang (412465)","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138254869","display_name":"Jingzhi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jingzhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138232408","display_name":"Yubin Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Yubin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5138218430","display_name":"Xingxing Wei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Xingxing","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":0.3409000039100647,"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":0.3409000039100647,"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":0.2971999943256378,"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.1712000072002411,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/spatial-intelligence","display_name":"Spatial intelligence","score":0.6967999935150146},{"id":"https://openalex.org/keywords/spatial-cognition","display_name":"Spatial cognition","score":0.5763999819755554},{"id":"https://openalex.org/keywords/cognitive-map","display_name":"Cognitive map","score":0.5681999921798706},{"id":"https://openalex.org/keywords/foundation","display_name":"Foundation (evidence)","score":0.5436000227928162},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.4611000120639801},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.44339999556541443},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4357999861240387},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.3930000066757202},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.38989999890327454},{"id":"https://openalex.org/keywords/spatial-learning","display_name":"Spatial learning","score":0.38449999690055847}],"concepts":[{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.6967999935150146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6513000130653381},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6157000064849854},{"id":"https://openalex.org/C2777371692","wikidata":"https://www.wikidata.org/wiki/Q2178611","display_name":"Spatial cognition","level":3,"score":0.5763999819755554},{"id":"https://openalex.org/C170494330","wikidata":"https://www.wikidata.org/wiki/Q1778434","display_name":"Cognitive map","level":3,"score":0.5681999921798706},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.5436000227928162},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4611000120639801},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4357999861240387},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.38989999890327454},{"id":"https://openalex.org/C2985665543","wikidata":"https://www.wikidata.org/wiki/Q3560550","display_name":"Spatial learning","level":3,"score":0.38449999690055847},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.3840999901294708},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.3677000105381012},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3628999888896942},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.337799996137619},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.33469998836517334},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.32690000534057617},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.30820000171661377},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3041999936103821},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30399999022483826},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.29170000553131104},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.28630000352859497},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.2655999958515167},{"id":"https://openalex.org/C2780226545","wikidata":"https://www.wikidata.org/wiki/Q6888030","display_name":"Modality (human\u2013computer interaction)","level":2,"score":0.2632000148296356},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.25780001282691956},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.2540000081062317}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.08952","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08952","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.2606.08952","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.08952","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Foundation":[1],"Models":[2],"(MFMs)":[3],"have":[4],"made":[5],"substantial":[6],"progress,":[7],"yet":[8],"remain":[9],"fragile":[10],"in":[11,22,49,116,140],"spatial":[12,34,47,149,168],"reasoning":[13,150,180],"over":[14],"the":[15],"physical":[16],"world.":[17],"A":[18],"key":[19],"bottleneck":[20],"lies":[21],"their":[23],"inability":[24],"to":[25],"transform":[26],"local":[27],"egocentric":[28,62],"observations":[29,63],"into":[30,64],"a":[31,55,98,123,141,182],"global":[32],"allocentric":[33,46,66,173],"representation.":[35],"To":[36,84],"address":[37],"this,":[38],"we":[39],"propose":[40],"AlloSpatial,":[41],"an":[42],"agentic":[43],"framework":[44],"for":[45,102],"cognition":[48],"foundation":[50,188],"models.":[51,189],"AlloSpatial":[52,96,134,159],"introduces":[53,97],"World2Mind,":[54],"plug-and-play":[56],"cognitive":[57],"mapping":[58],"sandbox":[59],"that":[60,74,133,171],"converts":[61],"structured":[65,172],"priors,":[67],"including":[68],"Allocentric-Spatial":[69],"Trees":[70],"and":[71,82,92,108,130,166,178],"route":[72,184],"maps":[73],"support":[75,147],"querying":[76],"object":[77],"topology,":[78],"geometric":[79],"relations,":[80],"passability,":[81],"trajectories.":[83],"utilize":[85],"these":[86],"priors":[87],"reliably":[88],"under":[89],"noisy":[90],"reconstruction":[91],"ambiguous":[93],"visual":[94,153],"evidence,":[95],"Spatial":[99],"Reasoning":[100],"Harness":[101],"tool-use":[103],"judgment,":[104],"modality-decoupled":[105],"cue":[106],"collection,":[107],"geometry-semantic":[109],"arbitration.":[110],"We":[111],"further":[112,161],"internalize":[113],"this":[114],"process":[115],"Qwen3-VL":[117],"through":[118],"cold-start":[119],"reinforcement":[120],"learning":[121],"with":[122],"harness-gated":[124],"trajectory-level":[125],"reward.":[126],"Experiments":[127],"on":[128],"VSI-Bench":[129],"MindCube":[131],"show":[132],"improves":[135],"proprietary":[136],"models":[137,165],"by":[138],"5%-18%":[139],"training-free":[142],"setting,":[143],"while":[144],"ASTs":[145],"alone":[146],"strong":[148],"even":[151],"when":[152],"inputs":[154],"are":[155],"removed.":[156],"The":[157],"trained":[158],"agents":[160],"outperform":[162],"larger":[163],"general-purpose":[164],"competitive":[167],"baselines,":[169],"suggesting":[170],"representations,":[174],"active":[175],"tool":[176],"use,":[177],"verifiable":[179],"offer":[181],"promising":[183],"toward":[185],"spatially":[186],"capable":[187]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-10T00:00:00"}