{"id":"https://openalex.org/W4405173422","doi":"https://doi.org/10.1109/wacv61042.2026.00144","title":"MageBench: Bridging Large Multimodal Models to Agents","display_name":"MageBench: Bridging Large Multimodal Models to Agents","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W4405173422","doi":"https://doi.org/10.1109/wacv61042.2026.00144"},"language":"en","primary_location":{"id":"doi:10.1109/wacv61042.2026.00144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.04531","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5070994294","display_name":"Miaosen Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Miaosen Zhang","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102317133","display_name":"Qi Dai","orcid":"https://orcid.org/0000-0002-8549-7225"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Qi Dai","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100743979","display_name":"Yifan Yang","orcid":"https://orcid.org/0000-0003-4801-0358"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yifan Yang","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101369681","display_name":"Jianmin Bao","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jianmin Bao","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100364591","display_name":"Dongdong Chen","orcid":"https://orcid.org/0000-0002-7016-9288"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dongdong Chen","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070412793","display_name":"Kai Qiu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kai Qiu","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101437627","display_name":"Chong Luo","orcid":"https://orcid.org/0000-0003-0939-474X"},"institutions":[{"id":"https://openalex.org/I4210164937","display_name":"Microsoft Research (United Kingdom)","ror":"https://ror.org/05k87vq12","country_code":"GB","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210164937"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Chong Luo","raw_affiliation_strings":["Microsoft"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft","institution_ids":["https://openalex.org/I4210164937"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101967108","display_name":"Xin Geng","orcid":"https://orcid.org/0000-0002-0015-0565"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Geng","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101666011","display_name":"Baining Guo","orcid":"https://orcid.org/0000-0001-8349-8868"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Baining Guo","raw_affiliation_strings":["Southeast University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Southeast University","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":0.00500819,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1415","last_page":"1427"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.43529999256134033,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.43529999256134033,"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/bridging","display_name":"Bridging (networking)","score":0.8985518217086792},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45390594005584717},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08769947290420532}],"concepts":[{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.8985518217086792},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45390594005584717},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08769947290420532}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/wacv61042.2026.00144","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00144","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2412.04531","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.04531","pdf_url":"https://arxiv.org/pdf/2412.04531","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},{"id":"doi:10.48550/arxiv.2412.04531","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.04531","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"pmh:oai:arXiv.org:2412.04531","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.04531","pdf_url":"https://arxiv.org/pdf/2412.04531","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W4388870064","https://openalex.org/W2210139803","https://openalex.org/W4235186151","https://openalex.org/W2054685365","https://openalex.org/W2056057048","https://openalex.org/W2667588871","https://openalex.org/W2272354214"],"abstract_inverted_index":{"Recent":[0],"models":[1,28,114],"like":[2],"OpenAI\u2019s":[3],"O1":[4],"and":[5,43,61,68,101,120,132,136],"DeepSeek\u2019s":[6],"R1,":[7],"which":[8],"utilize":[9],"test-time":[10],"scaling":[11],"techniques,":[12],"have":[13],"demonstrated":[14],"remarkable":[15],"improvements":[16],"in":[17,23,34,77,139],"reasoning":[18,89,99,152],"capabilities.":[19,153],"We":[20,130],"anticipate":[21],"that":[22,96,109,145,156],"the":[24,49,167],"near":[25],"future,":[26],"multimodal":[27,35,55,79],"will":[29,38],"also":[30],"experience":[31],"significant":[32,98],"breakthroughs":[33],"reasoning.":[36,71],"This":[37,154],"require":[39,59],"some":[40],"highly":[41],"challenging":[42],"specialized":[44],"evaluations.":[45],"As":[46],"one":[47],"of":[48,54,122,170],"most":[50],"crucial":[51],"real-world":[52],"applications":[53],"models,":[56],"visual":[57,140,151],"agents":[58],"complex":[60],"comprehensive":[62],"capabilities":[63,73],"such":[64],"as":[65,161],"spatial":[66],"planning":[67],"vision-in-the-chain":[69],"type":[70],"These":[72],"are":[74,115,124],"currently":[75],"lacking":[76],"existing":[78],"benchmarks.":[80],"In":[81],"this":[82],"paper,":[83],"we":[84,143],"introduce":[85],"MageBench,":[86],"a":[87,111,162],"Multimodal":[88],"benchmark":[90,158],"built":[91],"upon":[92],"light-weight":[93],"AGEnt":[94],"environments":[95],"pose":[97],"challenges":[100],"hold":[102],"substantial":[103],"practical":[104],"value.":[105],"The":[106],"results":[107],"show":[108],"only":[110],"few":[112],"product-level":[113],"better":[116],"than":[117],"random":[118],"acting,":[119],"all":[121],"them":[123],"far":[125],"inferior":[126],"to":[127],"human":[128],"level.":[129],"analyze":[131],"summarize":[133],"their":[134],"errors":[135],"capability":[137],"gaps":[138],"planning.":[141],"Furthermore,":[142],"found":[144],"rule-based":[146],"RL":[147,172],"can":[148],"significantly":[149],"boost":[150],"highlights":[155],"our":[157],"could":[159],"serve":[160],"valuable":[163],"testing":[164],"ground":[165],"for":[166],"emerging":[168],"field":[169],"agentic":[171],"research.":[173]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}