{"id":"https://openalex.org/W7133362126","doi":"https://doi.org/10.48550/arxiv.2603.00546","title":"Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation","display_name":"Advancing Multimodal Judge Models through a Capability-Oriented Benchmark and MCTS-Driven Data Generation","publication_year":2026,"publication_date":"2026-02-28","ids":{"openalex":"https://openalex.org/W7133362126","doi":"https://doi.org/10.48550/arxiv.2603.00546"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.00546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00546","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":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.00546","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127896835","display_name":"Zeyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Chen, Zeyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5127932717","display_name":"Huanjin Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Huanjin","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042424428","display_name":"Ziwang Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Ziwang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128011057","display_name":"Min Kyu Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Min","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5127896835"],"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":0.40799999237060547,"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":0.40799999237060547,"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":0.15199999511241913,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.12300000339746475,"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/benchmark","display_name":"Benchmark (surveying)","score":0.7311999797821045},{"id":"https://openalex.org/keywords/correctness","display_name":"Correctness","score":0.7218000292778015},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.6643999814987183},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6111999750137329},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5515999794006348},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5306000113487244},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4952000081539154},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.48339998722076416}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7781000137329102},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7311999797821045},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.7218000292778015},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6643999814987183},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6111999750137329},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5515999794006348},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5306000113487244},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.517799973487854},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5059000253677368},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4952000081539154},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.48339998722076416},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.45089998841285706},{"id":"https://openalex.org/C94124525","wikidata":"https://www.wikidata.org/wiki/Q912550","display_name":"Categorization","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C153701036","wikidata":"https://www.wikidata.org/wiki/Q659974","display_name":"Trustworthiness","level":2,"score":0.4097999930381775},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3472999930381775},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.2955000102519989},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.25380000472068787}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.00546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00546","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.00546","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.00546","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":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[{"score":0.5853172540664673,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Using":[0,145],"Multimodal":[1],"Large":[2],"Language":[3],"Models":[4],"(MLLMs)":[5],"as":[6,172,174],"judges":[7],"to":[8,48,69],"achieve":[9],"precise":[10],"and":[11,26,89,111,143,152,189,202],"consistent":[12],"evaluations":[13],"has":[14],"gradually":[15],"become":[16],"an":[17,149],"emerging":[18],"paradigm":[19],"across":[20,106],"various":[21,141],"domains.":[22],"Evaluating":[23],"the":[24,50,72,117,164,193],"capability":[25],"reliability":[27,105],"of":[28,75,103,157,166],"MLLM-as-a-judge":[29,122,186],"systems":[30],"is":[31],"therefore":[32],"essential":[33],"for":[34,55,184,195],"ensuring":[35],"trustworthy":[36],"assessment.":[37],"Existing":[38],"judge":[39,159,170,199,204],"benchmarks":[40,171],"categorize":[41],"samples":[42],"by":[43],"task":[44],"types":[45],"but":[46],"fail":[47],"capture":[49],"fundamental":[51],"judgment":[52,73],"capabilities":[53],"required":[54],"reliable":[56],"evaluation.":[57],"In":[58],"this":[59,126],"work,":[60],"we":[61,128,147],"introduce":[62],"M-JudgeBench,":[63],"a":[64,132,155,180],"ten-dimensional":[65],"capability-oriented":[66],"benchmark":[67,78],"designed":[68],"comprehensively":[70],"assess":[71],"abilities":[74],"MLLMs.":[76],"Our":[77],"decomposes":[79],"evaluation":[80,115,201],"into":[81],"pairwise":[82,137],"Chain-of-Thought":[83],"(CoT)":[84],"comparison,":[85],"length":[86],"bias":[87],"avoidance,":[88],"process":[90],"error":[91],"detection":[92],"tasks,":[93],"jointly":[94],"covering":[95],"ten":[96],"fine-grained":[97],"subtasks.":[98],"This":[99],"design":[100],"enables":[101],"diagnosis":[102],"model":[104,200],"reasoning":[107,138],"styles,":[108],"response":[109],"lengths,":[110],"cross-model":[112],"variations.":[113],"Systematic":[114],"uncovers":[116],"systematic":[118],"weaknesses":[119],"in":[120],"existing":[121,169],"systems.":[123],"To":[124],"address":[125],"issue,":[127],"further":[129],"propose":[130],"Judge-MCTS,":[131,146],"data":[133],"construction":[134],"framework":[135],"generating":[136],"trajectories":[139],"with":[140],"correctness":[142],"length.":[144],"construct":[148],"MCTS-augmented":[150],"dataset":[151],"train":[153],"M-Judger,":[154],"series":[156],"strong":[158],"models.":[160],"Extensive":[161],"experiments":[162],"demonstrate":[163],"superiority":[165],"M-Judger":[167],"on":[168,198],"well":[173],"M-JudgeBench.":[175],"Overall,":[176],"our":[177],"work":[178],"establishes":[179],"more":[181],"principled":[182],"foundation":[183],"evaluating":[185],"through":[187],"M-JudgeBench":[188],"Judge-MCTS":[190],"framework,":[191],"paving":[192],"way":[194],"future":[196],"research":[197],"capability-driven":[203],"training.":[205]},"counts_by_year":[],"updated_date":"2026-03-04T07:09:34.246503","created_date":"2026-03-04T00:00:00"}