{"id":"https://openalex.org/W7137861984","doi":"https://doi.org/10.48550/arxiv.2603.15030","title":"VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining","display_name":"VTC-Bench: Evaluating Agentic Multimodal Models via Compositional Visual Tool Chaining","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7137861984","doi":"https://doi.org/10.48550/arxiv.2603.15030"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.15030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15030","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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.2603.15030","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103097433","display_name":"Xuanyu Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhu, Xuanyu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129645828","display_name":"Yuhao Dong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong, Yuhao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129666331","display_name":"Rundong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Rundong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129733242","display_name":"Yang Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Yang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129672547","display_name":"Zhipeng Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Zhipeng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129703885","display_name":"Yinlun Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Yinlun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129725849","display_name":"Yifan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, YiFan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063901345","display_name":"Yihang Lou","orcid":"https://orcid.org/0000-0002-8143-389X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lou, Yihang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129706585","display_name":"Yuanxing Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuanxing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129684859","display_name":"Ziwei Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ziwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129726672","display_name":"Yan Bai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bai, Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129713448","display_name":"Yuan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Yuan","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5103097433"],"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":0.9772999882698059,"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":0.9772999882698059,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.003100000089034438,"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/T10028","display_name":"Topic Modeling","score":0.002099999925121665,"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/chaining","display_name":"Chaining","score":0.5911999940872192},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46779999136924744},{"id":"https://openalex.org/keywords/visual-language","display_name":"Visual language","score":0.39980000257492065},{"id":"https://openalex.org/keywords/computational-model","display_name":"Computational model","score":0.373199999332428},{"id":"https://openalex.org/keywords/plan","display_name":"Plan (archaeology)","score":0.3698999881744385},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.36000001430511475},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.35019999742507935},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.34549999237060547}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7918999791145325},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.5911999940872192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4733999967575073},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46779999136924744},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4325000047683716},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.39980000257492065},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3955000042915344},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.373199999332428},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.36000001430511475},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.35019999742507935},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.34549999237060547},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.32679998874664307},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.31040000915527344},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.30630001425743103},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.26179999113082886}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.15030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15030","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.15030","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.15030","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"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":{"Recent":[0],"advancements":[1],"extend":[2],"Multimodal":[3],"Large":[4],"Language":[5],"Models":[6],"(MLLMs)":[7],"beyond":[8],"standard":[9],"visual":[10,19,95,146,224],"question":[11],"answering":[12],"to":[13,48,76,105,152,154,159,186,217],"utilizing":[14],"external":[15],"tools":[16,30],"for":[17,31],"advanced":[18],"tasks.":[20],"Despite":[21],"this":[22,67],"progress,":[23],"precisely":[24],"executing":[25],"and":[26,41,51,110,157],"effectively":[27],"composing":[28],"diverse":[29,52,93,155],"complex":[32,50,182],"tasks":[33],"remain":[34],"persistent":[35,178],"bottleneck.":[36],"Constrained":[37],"by":[38],"sparse":[39],"tool-sets":[40,156],"simple":[42],"tool-use":[43,78],"trajectories,":[44],"existing":[45],"benchmarks":[46],"fail":[47],"capture":[49],"tool":[53],"interactions,":[54],"falling":[55],"short":[56],"in":[57,80,143],"evaluating":[58],"model":[59,165],"performance":[60],"under":[61],"practical,":[62],"real-world":[63],"conditions.":[64],"To":[65,82],"bridge":[66],"gap,":[68],"we":[69,118],"introduce":[70],"VisualToolChain-Bench(VTC-Bench),":[71],"a":[72,125,177,194,214],"comprehensive":[73],"benchmark":[74],"designed":[75],"evaluate":[77],"proficiency":[79],"MLLMs.":[81],"align":[83],"with":[84,130,162],"realistic":[85],"computer":[86],"vision":[87],"pipelines,":[88],"our":[89,171],"framework":[90],"features":[91],"32":[92],"OpenCV-based":[94],"operations.":[96],"This":[97],"rich":[98],"tool-set":[99],"enables":[100],"extensive":[101],"combinations,":[102],"allowing":[103],"VTC-Bench":[104,212],"rigorously":[106],"assess":[107],"multi-tool":[108,174],"composition":[109,175],"long-horizon,":[111],"multi-step":[112],"plan":[113],"execution.":[114],"For":[115],"precise":[116],"evaluation,":[117],"provide":[119],"680":[120],"curated":[121],"problems":[122],"structured":[123],"across":[124],"nine-category":[126],"cognitive":[127],"hierarchy,":[128],"each":[129],"ground-truth":[131],"execution":[132,189],"trajectories.":[133],"Extensive":[134],"experiments":[135],"on":[136,170,193],"19":[137],"leading":[138,164],"MLLMs":[139],"reveal":[140],"critical":[141],"limitations":[142],"current":[144],"models'":[145],"agentic":[147,225],"capabilities.":[148],"Specifically,":[149],"models":[150,184],"struggle":[151,185],"adapt":[153],"generalize":[158],"unseen":[160],"operations,":[161],"the":[163,204,219],"Gemini-3.0-Pro":[166],"only":[167],"achieving":[168],"51%":[169],"benchmark.":[172],"Furthermore,":[173],"remains":[176],"challenge.":[179],"When":[180],"facing":[181],"tasks,":[183],"formulate":[187],"efficient":[188],"plans,":[190],"relying":[191],"heavily":[192],"narrow,":[195],"suboptimal":[196],"subset":[197],"of":[198,221],"familiar":[199],"functions":[200],"rather":[201],"than":[202],"selecting":[203],"optimal":[205],"tools.":[206],"By":[207],"identifying":[208],"these":[209],"fundamental":[210],"challenges,":[211],"establishes":[213],"rigorous":[215],"baseline":[216],"guide":[218],"development":[220],"more":[222],"generalized":[223],"models.":[226]},"counts_by_year":[],"updated_date":"2026-03-21T06:30:42.041108","created_date":"2026-03-18T00:00:00"}