{"id":"https://openalex.org/W4416618367","doi":"https://doi.org/10.48550/arxiv.2510.20198","title":"Stuck in the Matrix: Probing Spatial Reasoning in Large Language Models","display_name":"Stuck in the Matrix: Probing Spatial Reasoning in Large Language Models","publication_year":2025,"publication_date":"2025-10-23","ids":{"openalex":"https://openalex.org/W4416618367","doi":"https://doi.org/10.48550/arxiv.2510.20198"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2510.20198","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.20198","pdf_url":"https://arxiv.org/pdf/2510.20198","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/2510.20198","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bai, Maggie","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Maggie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090387524","display_name":"Ava Kim Cohen","orcid":"https://orcid.org/0009-0004-8624-2541","observed_orcids":["https://orcid.org/0009-0004-8624-2541"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cohen, Ava Kim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120471507","display_name":"Eleanor Koss","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koss, Eleanor","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5120516981","display_name":"Charlie Lichtenbaum","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lichtenbaum, Charlie","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/T10028","display_name":"Topic Modeling","score":0.6093999743461609,"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"}},"topics":[{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.6093999743461609,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.22120000422000885,"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":0.0706000030040741,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spatial-reasoning","display_name":"spatial reasoning","score":0.8659999966621399},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":1.0},{"id":"https://openalex.org/keywords/multi-step-problem-solving","display_name":"multi-step problem solving","score":0.7570000290870667},{"id":"https://openalex.org/keywords/geometric-transformations","display_name":"geometric transformations","score":0.7879999876022339},{"id":"https://openalex.org/keywords/word-search-puzzles","display_name":"word search puzzles","score":0.6470000147819519},{"id":"https://openalex.org/keywords/scale-effects","display_name":"scale effects","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6829000115394592},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.5741999745368958},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.5223000049591064},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.5048999786376953},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48989999294281006},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.4803999960422516},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45089998841285706},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.41510000824928284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4025000035762787},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.3799999952316284},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.37450000643730164},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C2780297707","wikidata":"https://www.wikidata.org/wiki/Q4895393","display_name":"Landmark","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.27730000019073486},{"id":"https://openalex.org/C2983008078","wikidata":"https://www.wikidata.org/wiki/Q863495","display_name":"Grid cell","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C158709400","wikidata":"https://www.wikidata.org/wiki/Q3578586","display_name":"Spatial ecology","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.2581999897956848},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.25200000405311584}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2510.20198","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.20198","pdf_url":"https://arxiv.org/pdf/2510.20198","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.2510.20198","doi":"https://doi.org/10.48550/arxiv.2510.20198","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2510.20198","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2510.20198","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2510.20198","pdf_url":"https://arxiv.org/pdf/2510.20198","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0,161],"paper":[1,162],"explores":[2],"the":[3,137,141,164,181,188],"spatial":[4,25,37,81,155,169],"reasoning":[5,38,170],"capability":[6],"of":[7,18,113,132,140,153,190],"large":[8],"language":[9,191],"models":[10,31,72],"(LLMs)":[11],"over":[12,126],"textual":[13],"input":[14],"through":[15,67],"a":[16,130,151],"suite":[17],"five":[19],"tasks":[20,47,94],"aimed":[21],"at":[22,133,150,187],"probing":[23],"their":[24,144,158,176],"understanding":[26],"and":[27,39,58,98,115,168,179,192],"computational":[28],"abilities.":[29],"The":[30],"were":[32],"tested":[33],"on":[34],"both":[35],"fundamental":[36],"multi-step":[40],"problem-solving":[41],"within":[42],"structured":[43],"grid-based":[44],"environments":[45],"using":[46],"such":[48],"as":[49,104,117,119],"quadrant":[50],"identification,":[51],"geometric":[52],"transformations,":[53],"distance":[54],"evaluation,":[55],"word":[56],"searches,":[57],"tile":[59],"sliding.":[60],"Each":[61],"task":[62],"was":[63],"scaled":[64],"in":[65,92,111,157,171],"complexity":[66,97,148],"increasing":[68],"grid":[69],"dimensions,":[70],"requiring":[71],"to":[73],"extend":[74],"beyond":[75],"simple":[76],"pattern":[77],"recognition":[78],"into":[79,175],"abstract":[80],"reasoning.":[82],"Our":[83],"results":[84],"reveal":[85],"that":[86,123],"while":[87],"LLMs":[88],"demonstrate":[89],"moderate":[90],"success":[91],"all":[93],"with":[95,107,125,146],"small":[96],"size,":[99],"performance":[100],"drops":[101],"off":[102],"rapidly":[103],"scale":[105],"increases,":[106],"an":[108],"average":[109],"loss":[110,131],"accuracy":[112,128],"42.7%,":[114],"reaching":[116],"high":[118],"84%.":[120],"Every":[121],"test":[122],"began":[124],"50%":[127],"showed":[129],"least":[134],"48%,":[135],"illustrating":[136],"consistent":[138],"nature":[139],"deterioration.":[142],"Furthermore,":[143],"struggles":[145],"scaling":[147],"hint":[149],"lack":[152],"robust":[154],"representations":[156],"underlying":[159],"architectures.":[160],"underscores":[163],"gap":[165],"between":[166],"linguistic":[167],"LLMs,":[172],"offering":[173],"insights":[174],"current":[177],"limitations,":[178],"laying":[180],"groundwork":[182],"for":[183],"future":[184],"integrative":[185],"benchmarks":[186],"intersection":[189],"geometry.":[193]},"counts_by_year":[],"updated_date":"2026-09-26T08:19:03.415552","created_date":"2025-10-25T00:00:00"}