{"id":"https://openalex.org/W7154209938","doi":"https://doi.org/10.48550/arxiv.2604.09712","title":"LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models","display_name":"LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-04-08","ids":{"openalex":"https://openalex.org/W7154209938","doi":"https://doi.org/10.48550/arxiv.2604.09712"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2604.09712","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.09712","pdf_url":"https://arxiv.org/pdf/2604.09712","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/2604.09712","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130649096","display_name":"Shi-Yu Tian","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tian, Shi-Yu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133592221","display_name":"Zhi Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou, Zhi","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130652240","display_name":"Kun-Yang Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Kun-Yang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133611099","display_name":"Ming Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Ming","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133614489","display_name":"Yang Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Yang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113021202","display_name":"Ziqiao Shang","orcid":"https://orcid.org/0009-0006-0468-7497","observed_orcids":["https://orcid.org/0009-0006-0468-7497"]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shang, Ziqiao","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130197296","display_name":"Lan-Zhe Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Lan-Zhe","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130633883","display_name":"Yu-Feng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yu-Feng","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology , Nanjing University China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology , Nanjing University China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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":0.9994999766349792,"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":0.9994999766349792,"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":9.999999747378752e-05,"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":9.999999747378752e-05,"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/spatial-reasoning","display_name":"spatial reasoning","score":0.9850000143051147},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.9909999966621399},{"id":"https://openalex.org/keywords/tool-augmented-reasoning","display_name":"tool-augmented reasoning","score":0.8529999852180481},{"id":"https://openalex.org/keywords/tool-invocation","display_name":"tool invocation","score":0.7649999856948853},{"id":"https://openalex.org/keywords/hallucination-mitigation","display_name":"hallucination mitigation","score":0.6629999876022339},{"id":"https://openalex.org/keywords/segmentation-masks","display_name":"segmentation masks","score":0.6290000081062317},{"id":"https://openalex.org/keywords/depth-maps","display_name":"depth images","score":0.996999979019165},{"id":"https://openalex.org/keywords/progressive-training","display_name":"progressive training","score":0.46700000762939453},{"id":"https://openalex.org/keywords/spatial-ability","display_name":"spatial ability","score":0.7689999938011169}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8278999924659729},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.6988000273704529},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5956000089645386},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5877000093460083},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5706999897956848},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5257999897003174},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4706000089645386},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.461899995803833},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3785000145435333},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.31839999556541443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31700000166893005},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.3093000054359436},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.3066999912261963},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.29350000619888306},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C2780616401","wikidata":"https://www.wikidata.org/wiki/Q1133673","display_name":"Cornerstone","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C59519942","wikidata":"https://www.wikidata.org/wiki/Q650665","display_name":"Drone","level":2,"score":0.2644999921321869}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2604.09712","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.09712","pdf_url":"https://arxiv.org/pdf/2604.09712","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.2604.09712","doi":"https://doi.org/10.48550/arxiv.2604.09712","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.09712","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:2604.09712","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2604.09712","pdf_url":"https://arxiv.org/pdf/2604.09712","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7154209938.pdf","grobid_xml":"https://content.openalex.org/works/W7154209938.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W4226227340","https://openalex.org/W4385570924","https://openalex.org/W4389519818","https://openalex.org/W4391631327","https://openalex.org/W4399794484","https://openalex.org/W4403370767","https://openalex.org/W4407359463","https://openalex.org/W4407794264","https://openalex.org/W4413476030","https://openalex.org/W4414586680","https://openalex.org/W4414588912","https://openalex.org/W4415254741","https://openalex.org/W4415308770","https://openalex.org/W4415798372","https://openalex.org/W4415798746","https://openalex.org/W4416053382","https://openalex.org/W4416386285","https://openalex.org/W4416392771","https://openalex.org/W4416696005","https://openalex.org/W4416776696","https://openalex.org/W4417036176","https://openalex.org/W4417298859","https://openalex.org/W4417308961","https://openalex.org/W4417511763","https://openalex.org/W7075994152","https://openalex.org/W7131209732","https://openalex.org/W7138868077"],"related_works":["https://openalex.org/W7155041987","https://openalex.org/W7196947404","https://openalex.org/W7123654354","https://openalex.org/W7151556434","https://openalex.org/W4417308961","https://openalex.org/W7163537567","https://openalex.org/W4404782872","https://openalex.org/W7167073178","https://openalex.org/W7170369199","https://openalex.org/W7202181525"],"abstract_inverted_index":{"Spatial":[0],"reasoning":[1,63,193],"is":[2,64],"a":[3,52,106,152],"cornerstone":[4],"capability":[5],"for":[6,109],"intelligent":[7],"systems":[8],"to":[9,38,61,164],"perceive":[10],"and":[11,27,43,84,129,139,166,185],"interact":[12],"with":[13],"the":[14,80],"physical":[15],"world.":[16],"However,":[17],"multimodal":[18,134],"large":[19],"language":[20],"models":[21,50,159],"(MLLMs)":[22],"frequently":[23],"suffer":[24],"from":[25,160],"hallucinations":[26],"imprecision":[28],"when":[29],"parsing":[30],"complex":[31,195],"geometric":[32,41],"layouts.":[33],"As":[34],"data-driven":[35],"scaling":[36],"struggles":[37],"internalize":[39],"structured":[40],"priors":[42],"spatial":[44,62,111,131,196],"constraints,":[45],"integrating":[46],"mature,":[47],"specialized":[48],"vision":[49],"presents":[51],"compelling":[53],"alternative.":[54],"Despite":[55],"its":[56,183],"promise,":[57],"applying":[58],"this":[59],"paradigm":[60],"hindered":[65],"by":[66,147],"two":[67],"key":[68],"challenges:":[69],"The":[70],"difficulty":[71],"of":[72,82],"invoking":[73],"heterogeneous,":[74],"parameter-rich":[75],"tools,":[76],"as":[77,79],"well":[78],"challenge":[81],"understanding":[83,161],"effectively":[85],"leveraging":[86],"their":[87],"diverse":[88],"low-level":[89],"outputs":[90,163],"(e.g.,":[91,136],"segmentation":[92],"masks,":[93],"depth":[94],"maps)":[95],"in":[96],"high-level":[97],"reasoning.":[98,112],"To":[99],"address":[100],"these":[101],"challenges,":[102],"we":[103],"propose":[104],"LAST,":[105],"unified":[107],"framework":[108],"tool-augmented":[110],"LAST":[113],"features":[114],"an":[115],"extensible":[116],"interactive":[117],"sandbox,":[118],"termed":[119],"LAST-Box,":[120],"which":[121],"abstracts":[122],"heterogeneous":[123],"tool":[124,162,168],"invocations":[125],"into":[126],"atomic":[127],"instructions":[128],"reusable":[130],"skills,":[132],"returning":[133],"hints":[135],"annotated":[137],"images":[138],"textual":[140],"descriptions)":[141],"that":[142,157,175],"can":[143],"be":[144],"directly":[145],"consumed":[146],"LLMs.":[148],"We":[149],"further":[150],"design":[151],"three-stage":[153],"progressive":[154],"training":[155],"strategy":[156],"guides":[158],"proficient":[165],"adaptive":[167],"invocation.":[169],"Experiments":[170],"on":[171,194],"four":[172],"datasets":[173],"show":[174],"LAST-7B":[176],"achieves":[177],"around":[178],"20\\%":[179],"performance":[180],"gains":[181],"over":[182],"backbone":[184],"outperforms":[186],"strong":[187],"proprietary":[188],"closed-source":[189],"LLMs,":[190],"substantially":[191],"enhancing":[192],"tasks.":[197]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-04-15T00:00:00"}