{"id":"https://openalex.org/W7223051690","doi":"https://doi.org/10.48550/arxiv.2610.25247","title":"Visual Scaffolding: Toward Native Multimodal Reasoning","display_name":"Visual Scaffolding: Toward Native Multimodal Reasoning","publication_year":2026,"publication_date":"2026-10-18","ids":{"openalex":"https://openalex.org/W7223051690","doi":"https://doi.org/10.48550/arxiv.2610.25247"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.25247","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.25247","pdf_url":"https://arxiv.org/pdf/2610.25247","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.25247","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5111334880","display_name":"Run Shao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shao, Run","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159153772","display_name":"Zhaoyang Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhang, Zhaoyang","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159150388","display_name":"Ziyu Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Ziyu","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159137689","display_name":"Linrui Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Linrui","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003943585","display_name":"Ji Qi","orcid":"https://orcid.org/0000-0002-8548-116X","observed_orcids":["https://orcid.org/0000-0002-8548-116X"]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi, Ji","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159119351","display_name":"Xiu Su","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Su, Xiu","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5159123637","display_name":"Yichao Cao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cao, Yichao","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073640524","display_name":"Chao Tao","orcid":"https://orcid.org/0000-0003-0071-310X","observed_orcids":["https://orcid.org/0000-0003-0071-310X"]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao, Chao","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5159121490","display_name":"Haifeng Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I139660479","display_name":"Central South University","ror":"https://ror.org/00f1zfq44","country_code":"CN","type":"education","lineage":["https://openalex.org/I139660479"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Haifeng","raw_affiliation_strings":["Central South University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Central South University","institution_ids":["https://openalex.org/I139660479"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139660479"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":1.0,"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":1.0,"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":0.0,"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":0.0,"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/visual-scaffolding","display_name":"visual scaffolding","score":0.9229999780654907},{"id":"https://openalex.org/keywords/multimodal-reasoning","display_name":"multimodal reasoning","score":0.7760000228881836},{"id":"https://openalex.org/keywords/chain-of-thought","display_name":"chain-of-thought","score":0.9100000262260437},{"id":"https://openalex.org/keywords/multimodal-large-language-models","display_name":"multimodal large language models","score":0.8360000252723694},{"id":"https://openalex.org/keywords/visual-information-retrieval","display_name":"visual information retrieval","score":0.7649999856948853},{"id":"https://openalex.org/keywords/path-tracing","display_name":"path tracing","score":0.9750000238418579}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6966000199317932},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.5742999911308289},{"id":"https://openalex.org/C89429830","wikidata":"https://www.wikidata.org/wiki/Q735710","display_name":"Scaffold","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47850000858306885},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.43860000371932983},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4269999861717224},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.4219000041484833},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41530001163482666},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4034000039100647},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3986999988555908},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.3707999885082245},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.32760000228881836},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.3255000114440918},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2921000123023987},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.2825999855995178},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2784999907016754},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.27480000257492065},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2700999975204468},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.26980000734329224},{"id":"https://openalex.org/C207363949","wikidata":"https://www.wikidata.org/wiki/Q462915","display_name":"Visual space","level":3,"score":0.2574999928474426},{"id":"https://openalex.org/C194995250","wikidata":"https://www.wikidata.org/wiki/Q531136","display_name":"Affordance","level":2,"score":0.25459998846054077},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.25200000405311584},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.25247","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.25247","pdf_url":"https://arxiv.org/pdf/2610.25247","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.25247","doi":"https://doi.org/10.48550/arxiv.2610.25247","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.25247","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,"listed_in":[],"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.25247","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.25247","pdf_url":"https://arxiv.org/pdf/2610.25247","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,"listed_in":[],"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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7223051690.pdf","grobid_xml":"https://content.openalex.org/works/W7223051690.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4403791441","https://openalex.org/W7127346040","https://openalex.org/W4404783092","https://openalex.org/W4399026215","https://openalex.org/W7164016734","https://openalex.org/W7171872055","https://openalex.org/W7131683544","https://openalex.org/W7141460672","https://openalex.org/W4412945741","https://openalex.org/W7163208587"],"abstract_inverted_index":{"The":[0],"success":[1],"of":[2],"chain-of-thought":[3],"(CoT)":[4],"in":[5,53,82],"complex":[6],"reasoning":[7,79,81,114,215],"can":[8,19,192,211],"be":[9,20],"attributed":[10],"to":[11,25,51,135],"a":[12,33,70,95,109],"textual":[13],"scaffolding":[14,31,100],"effect:":[15],"explicit":[16],"intermediate":[17,92,214],"results":[18],"examined,":[21],"reused,":[22],"and":[23,87,132,152,167,175,191,217],"composed":[24],"support":[26],"subsequent":[27,136,194],"reasoning,":[28],"much":[29],"as":[30,80,213],"supports":[32],"building":[34],"under":[35,142],"construction.":[36],"However,":[37],"mainstream":[38],"multimodal":[39,78],"LLMs":[40],"lack":[41],"an":[42],"equivalent":[43],"scaffold":[44,72],"for":[45,73,222],"visual":[46,62,71,85,99,121,144,186,195,209],"distinctions":[47],"that":[48,183,207],"are":[49,124],"difficult":[50],"express":[52],"concise":[54],"verbal":[55],"descriptions.":[56],"We":[57,75],"therefore":[58],"ask:":[59],"Can":[60],"native":[61,77,84,120,208],"representations":[63,86],"become":[64],"first-class":[65],"citizens":[66],"alongside":[67],"language,":[68],"providing":[69],"reasoning?":[74],"define":[76],"which":[83,123],"language":[88],"jointly":[89],"carry":[90],"reusable":[91,220],"states.":[93],"As":[94],"concrete":[96],"implementation,":[97],"the":[98,105,129,172],"mechanism":[101,141],"we":[102,146],"proposed":[103],"lets":[104],"MLLM":[106],"autonomously":[107],"initiate":[108],"retrieval":[110],"action":[111],"at":[112],"any":[113],"step.":[115],"A":[116],"lightweight":[117],"retriever":[118],"selects":[119],"features,":[122],"then":[125],"incorporated":[126],"directly":[127],"into":[128],"evolving":[130],"CoT":[131],"remain":[133],"available":[134],"steps.":[137],"To":[138],"evaluate":[139],"this":[140],"controlled":[143],"demands,":[145],"introduce":[147],"NMR-Bench,":[148],"comprising":[149],"Burden":[150],"Counting":[151],"Path":[153],"Tracing.":[154],"With":[155],"88M":[156],"added":[157],"parameters":[158],"(approximately":[159],"2%)":[160],"on":[161],"Qwen3-VL-4B-Thinking,":[162],"our":[163],"model":[164],"achieves":[165],"66.43%":[166],"72.50%":[168],"accuracy,":[169],"respectively,":[170],"surpassing":[171],"evaluated":[173],"GPT-5.5":[174],"Gemini":[176],"3.1":[177],"Pro":[178],"baselines.":[179],"Controlled":[180],"interventions":[181],"show":[182,206],"changing":[184],"selected":[185],"content":[187],"affects":[188],"task":[189],"accuracy":[190],"redirect":[193],"selection":[196],"even":[197],"when":[198],"intervening":[199],"text":[200],"is":[201],"held":[202],"fixed.":[203],"These":[204],"findings":[205],"states":[210],"function":[212],"material":[216],"point":[218],"toward":[219],"scaffolds":[221],"additional":[223],"modalities.":[224]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-10-21T00:00:00"}
