{"id":"https://openalex.org/W7171984136","doi":"https://doi.org/10.48550/arxiv.2607.27703","title":"SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them","display_name":"SpatialCLI: Learning to Reason With Spatial Tools, Then Without Them","publication_year":2026,"publication_date":"2026-07-30","ids":{"openalex":"https://openalex.org/W7171984136","doi":"https://doi.org/10.48550/arxiv.2607.27703"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2607.27703","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.27703","pdf_url":"https://arxiv.org/pdf/2607.27703","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2607.27703","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128137254","display_name":"Yang Zhou","orcid":"https://orcid.org/0000-0002-8921-312X","observed_orcids":["https://orcid.org/0000-0002-8921-312X"]},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Yang","raw_affiliation_strings":["Zhejiang University ,","Zhuoyu Technology , Shenzhen , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University ,","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"Zhuoyu Technology , Shenzhen , China,","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137529762","display_name":"Zixuan Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Zixuan","raw_affiliation_strings":["Beihang University","Zhuoyu Technology , Shenzhen , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]},{"raw_affiliation_string":"Zhuoyu Technology , Shenzhen , China,","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144117877","display_name":"Sunzhu Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Sunzhu","raw_affiliation_strings":["Zhuoyu Technology , Shenzhen , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhuoyu Technology , Shenzhen , China,","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144162084","display_name":"Zhuo Yang","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":"Yang, Zhuo","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/A5150948344","display_name":"Chen Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Chen","raw_affiliation_strings":["Zhejiang University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University ,","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5144090833","display_name":"Shunian Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]},{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Shunian","raw_affiliation_strings":["The Chinese University of Hong Kong , Shenzhen","Zhuoyu Technology , Shenzhen , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong , Shenzhen","institution_ids":["https://openalex.org/I4210116924"]},{"raw_affiliation_string":"Zhuoyu Technology , Shenzhen , China,","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000025337","display_name":"\u4e25\u5f69\u541b","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan, Caijun","raw_affiliation_strings":["Zhejiang University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University ,","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102150688","display_name":"Jianyao Xu","orcid":"https://orcid.org/0009-0001-1007-8595","observed_orcids":["https://orcid.org/0009-0001-1007-8595"]},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Jianyao","raw_affiliation_strings":["Zhuoyu Technology , Shenzhen , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhuoyu Technology , Shenzhen , China,","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090854835","display_name":"Shunyu Liu","orcid":"https://orcid.org/0000-0003-0584-9129","observed_orcids":["https://orcid.org/0000-0003-0584-9129","https://orcid.org/0009-0009-5289-1400"]},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Liu, Shunyu","raw_affiliation_strings":["Nanyang Technological University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nanyang Technological University","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153491881","display_name":"Weijie Fu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu, Weijie","raw_affiliation_strings":["Zhuoyu Technology , Shenzhen , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhuoyu Technology , Shenzhen , China,","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016925825","display_name":"Peiliang Li","orcid":"https://orcid.org/0000-0001-5839-8777","observed_orcids":["https://orcid.org/0000-0001-5839-8777"]},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Peiliang","raw_affiliation_strings":["Zhuoyu Technology , Shenzhen , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhuoyu Technology , Shenzhen , China,","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129852707","display_name":"Xiaozhi Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210152380","display_name":"Shenzhen Technology University","ror":"https://ror.org/04qzpec27","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210152380"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Xiaozhi","raw_affiliation_strings":["Zhuoyu Technology , Shenzhen , China,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhuoyu Technology , Shenzhen , China,","institution_ids":["https://openalex.org/I4210152380"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040589965","display_name":"Yuxiang Cai","orcid":"https://orcid.org/0000-0003-2784-6607","observed_orcids":["https://orcid.org/0000-0003-2784-6607"]},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cai, Yuxiang","raw_affiliation_strings":["Zhejiang University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University ,","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":0.9779999852180481,"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":0.9779999852180481,"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":0.01889999955892563,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.0005000000237487257,"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/vision-language-models","display_name":"vision-language models","score":0.921999990940094},{"id":"https://openalex.org/keywords/tool-use","display_name":"tool use","score":0.7070000171661377},{"id":"https://openalex.org/keywords/embodied-agents","display_name":"embodied agents","score":0.7490000128746033},{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.5730000138282776},{"id":"https://openalex.org/keywords/agentic-reinforcement-learning","display_name":"agentic reinforcement learning","score":0.9700000286102295},{"id":"https://openalex.org/keywords/localization","display_name":"localization","score":0.44600000977516174},{"id":"https://openalex.org/keywords/segmentation","display_name":"segmentation","score":0.7039999961853027},{"id":"https://openalex.org/keywords/depth-estimation","display_name":"depth estimation","score":0.9330000281333923},{"id":"https://openalex.org/keywords/pose-estimation","display_name":"pose estimation","score":0.9169999957084656},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5849999785423279},{"id":"https://openalex.org/keywords/qwen3-vl","display_name":"Qwen3-VL","score":0.9020000100135803}],"concepts":[{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.7297000288963318},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6474999785423279},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6428999900817871},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.5662999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5257999897003174},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.47749999165534973},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44440001249313354},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3160000145435333},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.28049999475479126},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.27090001106262207},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.2669000029563904},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.26159998774528503},{"id":"https://openalex.org/C2776010242","wikidata":"https://www.wikidata.org/wiki/Q4677575","display_name":"Active perception","level":3,"score":0.25519999861717224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2547000050544739}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2607.27703","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.27703","pdf_url":"https://arxiv.org/pdf/2607.27703","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2607.27703","doi":"https://doi.org/10.48550/arxiv.2607.27703","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.27703","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2607.27703","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.27703","pdf_url":"https://arxiv.org/pdf/2607.27703","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":null,"license_id":null,"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/W7171984136.pdf","grobid_xml":"https://content.openalex.org/works/W7171984136.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417036176","https://openalex.org/W7164505148","https://openalex.org/W7104817213","https://openalex.org/W4416034987","https://openalex.org/W7172404806","https://openalex.org/W4417495068","https://openalex.org/W7165378724","https://openalex.org/W7164577342","https://openalex.org/W7223114576","https://openalex.org/W4400373871"],"abstract_inverted_index":{"Vision-language":[0],"models":[1,51,98],"(VLMs)":[2],"are":[3],"increasingly":[4],"used":[5],"in":[6,90],"embodied":[7],"agents":[8],"to":[9,74,102,115,126,154],"interpret":[10],"visual":[11,43],"inputs,":[12],"reason":[13,34,75],"about":[14,35],"spatial":[15,77,100],"relationships,":[16],"and":[17,79,112,119,145],"make":[18],"task-level":[19,61],"decisions":[20],"based":[21],"on":[22],"that":[23,45,71],"reasoning.":[24],"However,":[25],"a":[26,69,135],"fundamental":[27],"capability":[28],"mismatch":[29],"remains:":[30],"general":[31],"VLMs":[32,73],"can":[33,52],"the":[36,42,82,104],"overall":[37],"task":[38],"but":[39,56],"often":[40],"miss":[41],"details":[44,55],"determine":[46],"success,":[47],"while":[48,164],"specialist":[49,83,96,128],"vision":[50,97],"capture":[53],"those":[54],"cannot":[57],"translate":[58],"them":[59],"into":[60],"decisions.":[62],"In":[63],"this":[64],"work,":[65],"we":[66],"propose":[67],"SpatialCLI,":[68],"framework":[70],"teaches":[72],"with":[76,156,161],"tools":[78,101,162,168],"progressively":[80],"internalize":[81,127],"perceptual":[84,129],"capabilities":[85],"they":[86],"provide.":[87],"SpatialCLI":[88,149],"proceeds":[89],"three":[91],"stages:":[92],"(1)":[93],"Call":[94],"exposes":[95],"as":[99],"augment":[103],"VLM's":[105],"perception;":[106],"(2)":[107],"Learn":[108],"uses":[109],"Cold-Start":[110],"SFT":[111],"agentic":[113],"RL":[114],"improve":[116],"tool":[117],"use;":[118],"(3)":[120],"Internalize":[121],"verbalizes":[122],"successful":[123],"tool-use":[124],"trajectories":[125],"capabilities.":[130],"We":[131],"further":[132],"introduce":[133],"SpatialCLI-Bench,":[134],"516-example":[136],"benchmark":[137],"for":[138],"compositional":[139],"perception":[140],"across":[141],"localization,":[142],"segmentation,":[143],"depth,":[144],"pose.":[146],"On":[147],"MindCube,":[148],"raises":[150],"Qwen3-VL-8B-Instruct":[151],"from":[152],"29.3%":[153],"84.6%":[155],"tools,":[157],"surpassing":[158],"GPT-5.6":[159],"Sol":[160],"(72.1%),":[163],"retaining":[165],"73.8%":[166],"without":[167],"after":[169],"internalization.":[170]},"counts_by_year":[],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2026-08-01T00:00:00"}
