{"id":"https://openalex.org/W4417092583","doi":"https://doi.org/10.18653/v1/2026.findings-acl.878","title":"V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models","display_name":"V-MAGE: A Game Evaluation Framework for Assessing Vision-Centric Capabilities in Multimodal Large Language Models","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W4417092583","doi":"https://doi.org/10.18653/v1/2026.findings-acl.878"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2026.findings-acl.878","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.878","pdf_url":"https://aclanthology.org/2026.findings-acl.878.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.findings-acl.878.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiangxi Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangxi Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110673725","display_name":"Linjie Li","orcid":"https://orcid.org/0000-0002-9817-1793"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Linjie Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050209478","display_name":"Zhengyuan Yang","orcid":"https://orcid.org/0000-0002-5808-0889"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengyuan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110241468","display_name":"Ping Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032671650","display_name":"Alex Jinpeng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alex Jinpeng Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046836420","display_name":"Rui Yan","orcid":"https://orcid.org/0000-0003-0048-3092"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rui Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019214642","display_name":"Yuan Yao","orcid":"https://orcid.org/0000-0002-6282-342X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan Yao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5101406479","display_name":"Lijuan Wang","orcid":"https://orcid.org/0000-0001-9813-9075"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lijuan Wang","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.02773543,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"17707","last_page":"17758"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9336000084877014,"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":0.9336000084877014,"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/T10028","display_name":"Topic Modeling","score":0.011599999852478504,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.004600000102072954,"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/benchmarking","display_name":"Benchmarking","score":0.6082000136375427},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5992000102996826},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5622000098228455},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.5037999749183655},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.47040000557899475},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.3977999985218048},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.3513999879360199},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3495999872684479}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8082000017166138},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6082000136375427},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5992000102996826},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5622000098228455},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5037999749183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49900001287460327},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.47040000557899475},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4683000147342682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4634999930858612},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3977999985218048},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.26570001244544983},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.258899986743927},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2026.findings-acl.878","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.878","pdf_url":"https://aclanthology.org/2026.findings-acl.878.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2504.06148","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2504.06148","pdf_url":"https://arxiv.org/pdf/2504.06148","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":"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.2504.06148","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2504.06148","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":"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":"doi:10.18653/v1/2026.findings-acl.878","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.findings-acl.878","pdf_url":"https://aclanthology.org/2026.findings-acl.878.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: ACL 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320324852","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4417092583.pdf","grobid_xml":"https://content.openalex.org/works/W4417092583.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,11,48,67,133,140,155,165,177,194],"Multimodal":[3],"LargeLanguage":[4],"Models":[5],"(MLLMs)":[6],"have":[7],"demonstrated":[8],"impressive":[9],"capabilities":[10,191],"visual-text":[12],"processing.However,":[13],"existing":[14],"static":[15],"image-text":[16],"benchmarks":[17],"are":[18,65],"insufficient":[19],"for":[20,113,185],"evaluating":[21],"their":[22,136],"dynamic":[23,77,107],"perception":[24],"and":[25,80,99,117,146,181,189],"interactive":[26,162,196],"reasoning":[27,47,145,190],"abilities.We":[28],"introduce":[29],"Vision-centric":[30],"Multiple":[31],"Abilities":[32],"Game":[33],"Evaluation":[34],"(V-MAGE),":[35],"a":[36,106],"novel":[37],"game-based":[38],"evaluation":[39,62],"framework":[40],"designed":[41],"to":[42,75,159],"systematically":[43],"assess":[44],"MLLMs'":[45,157],"visual":[46,86,188],"interactive,":[49],"continuous-space":[50],"environments.V-MAGE":[51],"features":[52],"five":[53],"distinct":[54],"video":[55],"games":[56],"comprising":[57],"over":[58],"30":[59],"carefully":[60],"constructed":[61],"scenarios.These":[63],"scenarios":[64,142],"set":[66],"free-form,":[68],"visually":[69],"complex":[70,141],"environments":[71],"that":[72,111,126],"require":[73],"models":[74,129],"interpret":[76],"game":[78],"states":[79],"make":[81],"decisions":[82],"based":[83],"solely":[84],"on":[85],"input,":[87],"thereby":[88],"closely":[89],"reflecting":[90],"the":[91,173,187],"conditions":[92],"encountered":[93],"by":[94],"human":[95,123],"players.To":[96],"ensure":[97],"robust":[98],"interpretable":[100],"comparisons":[101],"across":[102],"models,":[103],"V-MAGE":[104,176],"employs":[105],"ELO-based":[108],"ranking":[109],"system":[110],"accounts":[112],"varying":[114],"difficulty":[115],"levels":[116],"task":[118,147],"diversity.Benchmarking":[119],"state-of-the-art":[120],"MLLMs":[121,193],"against":[122],"baselines":[124],"reveals":[125],"while":[127],"leading":[128],"approach":[130],"human-level":[131],"performance":[132,137,150],"simple":[134],"tasks,":[135],"drops":[138],"significantly":[139],"requiring":[143],"advanced":[144],"orchestration.This":[148],"persistent":[149],"gap":[151],"highlights":[152],"fundamental":[153],"limitations":[154,180],"current":[156],"ability":[158],"perform":[160],"vision-grounded,":[161],"frameby-frame":[163],"control":[164],"simulated":[166],"continuous-time":[167],"environments.Through":[168],"extensive":[169],"analyses,":[170],"we":[171],"demonstrate":[172],"utility":[174],"of":[175,192],"uncovering":[178],"these":[179],"providing":[182],"actionable":[183],"insights":[184],"improving":[186],"dynamic,":[195],"settings.":[197]},"counts_by_year":[],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}