{"id":"https://openalex.org/W7163220138","doi":"https://doi.org/10.48550/arxiv.2606.02357","title":"Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains","display_name":"Do Multimodal Agents Really Benefit from Tool Use? A Systematic Study of Capability Gains","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163220138","doi":"https://doi.org/10.48550/arxiv.2606.02357"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.02357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02357","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.02357","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137678630","display_name":"Garvin Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Garvin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137625790","display_name":"Donglei Yu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yu, Donglei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137679490","display_name":"Yu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137644321","display_name":"Xiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Xiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137686938","display_name":"Shuai Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102636467","display_name":"Xinpei Zhao","orcid":"https://orcid.org/0009-0000-6597-7582"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Xinpei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136739034","display_name":"Huaxing Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Huaxing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137711700","display_name":"Qinghao Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Qinghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5073673415","display_name":"Minpeng Liao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Minpeng","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":0.5964999794960022,"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":0.5964999794960022,"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":0.05119999870657921,"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":0.038100000470876694,"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":0.5519000291824341},{"id":"https://openalex.org/keywords/aggregate","display_name":"Aggregate (composite)","score":0.5146999955177307},{"id":"https://openalex.org/keywords/semantic-reasoner","display_name":"Semantic reasoner","score":0.47440001368522644},{"id":"https://openalex.org/keywords/mechanism","display_name":"Mechanism (biology)","score":0.4530999958515167},{"id":"https://openalex.org/keywords/trace","display_name":"TRACE (psycholinguistics)","score":0.44999998807907104},{"id":"https://openalex.org/keywords/interpretation","display_name":"Interpretation (philosophy)","score":0.4327999949455261}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7071999907493591},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5519000291824341},{"id":"https://openalex.org/C4679612","wikidata":"https://www.wikidata.org/wiki/Q866298","display_name":"Aggregate (composite)","level":2,"score":0.5146999955177307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5090000033378601},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48489999771118164},{"id":"https://openalex.org/C9616225","wikidata":"https://www.wikidata.org/wiki/Q3929429","display_name":"Semantic reasoner","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.44999998807907104},{"id":"https://openalex.org/C527412718","wikidata":"https://www.wikidata.org/wiki/Q855395","display_name":"Interpretation (philosophy)","level":2,"score":0.4327999949455261},{"id":"https://openalex.org/C190812933","wikidata":"https://www.wikidata.org/wiki/Q28923","display_name":"Chart","level":2,"score":0.38370001316070557},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.320499986410141},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.25220000743865967},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.25209999084472656},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.25029999017715454}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.02357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02357","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":"doi:10.48550/arxiv.2606.02357","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02357","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Tool-augmented":[0],"multimodal":[1],"agents":[2,12,150,174],"show":[3,32,123],"strong":[4],"benchmark":[5],"gains,":[6],"often":[7],"taken":[8],"as":[9],"evidence":[10],"that":[11,20,124,162],"have":[13],"learned":[14],"to":[15,152],"use":[16],"tools.":[17],"We":[18,39],"argue":[19],"this":[21],"interpretation":[22],"can":[23,175],"be":[24],"premature:":[25],"a":[26,69,97],"tool-call":[27,135],"trace":[28],"alone":[29],"does":[30,88,129],"not":[31,89,130],"whether":[33,169],"the":[34,74,125,134,138,144,148],"tool":[35,166],"supplied":[36],"answer-critical":[37],"information.":[38],"study":[40],"two":[41],"representative":[42],"``thinking":[43],"with":[44,63,68],"images''":[45],"agents,":[46],"Thyme":[47],"and":[48,56,67,94,107],"DeepEyesV2,":[49],"across":[50],"real-world":[51],"understanding,":[52,55],"OCR,":[53],"chart":[54],"mathematical":[57],"reasoning.":[58],"Each":[59],"agent":[60],"is":[61],"compared":[62],"its":[64],"Tool-Free":[65],"counterpart":[66],"Pure-Text":[70],"Reasoner":[71],"trained":[72],"from":[73,168],"same":[75],"source":[76],"pool":[77],"without":[78],"tool-calling":[79,154],"trajectories.":[80],"Tool":[81],"access":[82],"yields":[83],"little":[84],"consistent":[85],"aggregate":[86],"improvement,":[87],"reliably":[90,157],"reduce":[91],"generated-token":[92],"cost,":[93],"leaves":[95],"only":[96],"small":[98],"tool-only":[99],"solved":[100,113],"set:":[101],"93%":[102],"of":[103,109],"DeepEyesV2's":[104],"tool-solved":[105],"problems":[106],"96%":[108],"Thyme's":[110],"are":[111],"also":[112],"by":[114],"at":[115],"least":[116],"one":[117],"non-tool":[118],"setting.":[119],"Mechanism":[120],"ablations":[121],"further":[122],"full":[126],"tool-use":[127],"loop":[128],"consistently":[131],"outperform":[132],"either":[133],"format":[136],"or":[137],"returned":[139],"execution":[140],"result":[141],"alone.":[142],"In":[143],"settings":[145],"we":[146],"study,":[147],"analyzed":[149],"appear":[151],"learn":[153],"patterns":[155],"more":[156],"than":[158],"tool-contributed":[159],"capabilities,":[160],"suggesting":[161],"evaluation":[163],"should":[164],"distinguish":[165],"availability":[167],"tools":[170],"actually":[171],"expand":[172],"what":[173],"solve.":[176]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}