{"id":"https://openalex.org/W7106217546","doi":"https://doi.org/10.48550/arxiv.2511.15065","title":"Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks","display_name":"Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks","publication_year":2025,"publication_date":"2025-11-19","ids":{"openalex":"https://openalex.org/W7106217546","doi":"https://doi.org/10.48550/arxiv.2511.15065"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2511.15065","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.15065","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,"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.2511.15065","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yang, Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wan, Haiyuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wan, Haiyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Peng, Yiran","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Yiran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Cheng, Xin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheng, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yu, Zhaoyang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Zhaoyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Jiayi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiayi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yu, Junchi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Junchi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yu, Xinlei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Xinlei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zheng, Xiawu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Xiawu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhou, Dongzhan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Dongzhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Wu, Chenglin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Chenglin","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":0.8772000074386597,"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":0.8772000074386597,"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/T12290","display_name":"Human Motion and Animation","score":0.03959999978542328,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.02370000071823597,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spatial-intelligence","display_name":"Spatial intelligence","score":0.671500027179718},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6302000284194946},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.47040000557899475},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.46239998936653137},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.45339998602867126},{"id":"https://openalex.org/keywords/video-tracking","display_name":"Video tracking","score":0.4074000120162964},{"id":"https://openalex.org/keywords/motion","display_name":"Motion (physics)","score":0.38769999146461487},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.37369999289512634}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.741599977016449},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.671500027179718},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6302000284194946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5651999711990356},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.46239998936653137},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C202474056","wikidata":"https://www.wikidata.org/wiki/Q1931635","display_name":"Video tracking","level":3,"score":0.4074000120162964},{"id":"https://openalex.org/C104114177","wikidata":"https://www.wikidata.org/wiki/Q79782","display_name":"Motion (physics)","level":2,"score":0.38769999146461487},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.37369999289512634},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.3725999891757965},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.31209999322891235},{"id":"https://openalex.org/C27511587","wikidata":"https://www.wikidata.org/wiki/Q2178623","display_name":"Spatial relation","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.29660001397132874},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.28839999437332153},{"id":"https://openalex.org/C117090137","wikidata":"https://www.wikidata.org/wiki/Q7927977","display_name":"Video post-processing","level":5,"score":0.2797999978065491},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2768000066280365},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.2694999873638153},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C65483669","wikidata":"https://www.wikidata.org/wiki/Q3536669","display_name":"Video processing","level":2,"score":0.2565999925136566},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.2554999887943268}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2511.15065","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.15065","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,"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.2511.15065","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2511.15065","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,"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":{"Video":[0,134],"Models":[1],"have":[2],"achieved":[3],"remarkable":[4],"success":[5],"in":[6,24,52,94],"high-fidelity":[7],"video":[8,30,37,41,49,76,89,132,184],"generation":[9,20],"with":[10,44],"coherent":[11],"motion":[12],"dynamics.":[13],"Analogous":[14],"to":[15,21,34,86],"the":[16,27,45,73,128,176],"development":[17,28],"from":[18],"text":[19,47],"text-based":[22],"reasoning":[23,51,74,91,129,169,182,187],"language":[25],"modeling,":[26],"of":[29,131,154,181],"models":[31,38,135],"motivates":[32],"us":[33],"ask:":[35],"Can":[36],"reason":[39],"via":[40,75,183],"generation?":[42],"Compared":[43],"discrete":[46],"corpus,":[48],"grounds":[50],"explicit":[53],"spatial":[54,66,100,138,186],"layouts":[55],"and":[56,78,102,115,145,152,179],"temporal":[57],"continuity,":[58],"which":[59],"serves":[60],"as":[61],"an":[62],"ideal":[63],"substrate":[64],"for":[65,185],"reasoning.":[67],"In":[68],"this":[69],"work,":[70],"we":[71],"explore":[72],"paradigm":[77],"introduce":[79],"VR-Bench":[80,105],"--":[81],"a":[82,159],"comprehensive":[83],"benchmark":[84],"designed":[85],"systematically":[87],"evaluate":[88],"models'":[90],"capabilities.":[92],"Grounded":[93],"maze-solving":[95],"tasks":[96],"that":[97,123],"inherently":[98],"require":[99],"planning":[101],"multi-step":[103],"reasoning,":[104,141],"contains":[106],"7,920":[107],"procedurally":[108],"generated":[109],"videos":[110],"across":[111,148],"five":[112],"maze":[113],"types":[114],"diverse":[116,149,164],"visual":[117],"styles.":[118],"Our":[119],"empirical":[120],"analysis":[121],"demonstrates":[122],"SFT":[124],"can":[125],"efficiently":[126],"elicit":[127],"ability":[130],"model.":[133],"exhibit":[136],"stronger":[137],"perception":[139],"during":[140,166],"outperforming":[142],"leading":[143],"VLMs":[144],"generalizing":[146],"well":[147],"scenarios,":[150],"tasks,":[151],"levels":[153],"complexity.":[155],"We":[156],"further":[157],"discover":[158],"test-time":[160],"scaling":[161],"effect,":[162],"where":[163],"sampling":[165],"inference":[167],"improves":[168],"reliability":[170],"by":[171],"10--20%.":[172],"These":[173],"findings":[174],"highlight":[175],"unique":[177],"potential":[178],"scalability":[180],"tasks.":[188]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-11-23T00:00:00"}