{"id":"https://openalex.org/W6929541986","doi":"https://doi.org/10.48550/arxiv.2503.12605","title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","display_name":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","publication_year":2025,"publication_date":"2025-03-16","ids":{"openalex":"https://openalex.org/W6929541986","doi":"https://doi.org/10.48550/arxiv.2503.12605"},"language":"en","primary_location":{"id":"doi:10.48550/arxiv.2503.12605","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.12605","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.2503.12605","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Wang, Yaoting","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wang, Yaoting","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wu, Shengqiong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Shengqiong","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Yuecheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yuecheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Yan, Shuicheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yan, Shuicheng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Ziwei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Ziwei","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Luo, Jiebo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Jiebo","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Fei, Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fei, Hao","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"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":true,"primary_topic":{"id":"https://openalex.org/T10407","display_name":"Lipid Membrane Structure and Behavior","score":0.2110999971628189,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T10407","display_name":"Lipid Membrane Structure and Behavior","score":0.2110999971628189,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10540","display_name":"Advanced Fluorescence Microscopy Techniques","score":0.04610000178217888,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10063","display_name":"Nanoparticle-Based Drug Delivery","score":0.03290000185370445,"subfield":{"id":"https://openalex.org/subfields/2502","display_name":"Biomaterials"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.41769999265670776},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4171999990940094},{"id":"https://openalex.org/keywords/taxonomy","display_name":"Taxonomy (biology)","score":0.4140999913215637},{"id":"https://openalex.org/keywords/multimodality","display_name":"Multimodality","score":0.3806999921798706},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.3749000132083893},{"id":"https://openalex.org/keywords/multimodal-interaction","display_name":"Multimodal interaction","score":0.34139999747276306}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5895000100135803},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4431000053882599},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.41769999265670776},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.4140999913215637},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3783000111579895},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.3749000132083893},{"id":"https://openalex.org/C135641252","wikidata":"https://www.wikidata.org/wiki/Q738567","display_name":"Multimodal interaction","level":2,"score":0.34139999747276306},{"id":"https://openalex.org/C2776745293","wikidata":"https://www.wikidata.org/wiki/Q7798302","display_name":"Thriving","level":2,"score":0.3224000036716461},{"id":"https://openalex.org/C547195049","wikidata":"https://www.wikidata.org/wiki/Q1725664","display_name":"Terminology","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.28380000591278076},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2718999981880188},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.2628999948501587},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2606000006198883},{"id":"https://openalex.org/C189708586","wikidata":"https://www.wikidata.org/wiki/Q1504425","display_name":"Systematic review","level":3,"score":0.25609999895095825},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2503.12605","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.12605","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.2503.12605","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.12605","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":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6831926107406616}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"By":[0],"extending":[1],"the":[2,27,47,111,119],"advantage":[3],"of":[4,50,100,115,134],"chain-of-thought":[5],"(CoT)":[6],"reasoning":[7,18,43],"in":[8,26,65,92],"human-like":[9],"step-by-step":[10],"processes":[11],"to":[12,45,88,156],"multimodal":[13,15,30,74,160],"contexts,":[14],"CoT":[16],"(MCoT)":[17],"has":[19],"recently":[20],"garnered":[21],"significant":[22],"research":[23,153],"attention,":[24],"especially":[25],"integration":[28],"with":[29],"large":[31],"language":[32],"models":[33],"(MLLMs).":[34],"Existing":[35],"MCoT":[36,77,116],"studies":[37],"design":[38],"various":[39,141],"methodologies":[40,136],"and":[41,56,73,82,123,130,151],"innovative":[42],"paradigms":[44],"address":[46],"unique":[48],"challenges":[49,81,150],"image,":[51],"video,":[52],"speech,":[53],"audio,":[54],"3D,":[55],"structured":[57],"data":[58],"across":[59,140],"different":[60],"modalities,":[61],"achieving":[62],"extensive":[63],"success":[64],"applications":[66],"such":[67],"as":[68],"robotics,":[69],"healthcare,":[70],"autonomous":[71],"driving,":[72],"generation.":[75],"However,":[76],"still":[78],"presents":[79],"distinct":[80],"opportunities":[83],"that":[84],"require":[85],"further":[86],"focus":[87],"ensure":[89],"consistent":[90],"thriving":[91],"this":[93,101,107],"field,":[94],"where,":[95],"unfortunately,":[96],"an":[97,131],"up-to-date":[98],"review":[99],"domain":[102],"is":[103],"lacking.":[104],"To":[105],"bridge":[106],"gap,":[108],"we":[109,145],"present":[110],"first":[112],"systematic":[113],"survey":[114],"reasoning,":[117],"elucidating":[118],"relevant":[120],"foundational":[121],"concepts":[122],"definitions.":[124],"We":[125],"offer":[126],"a":[127],"comprehensive":[128],"taxonomy":[129],"in-depth":[132],"analysis":[133],"current":[135],"from":[137],"diverse":[138],"perspectives":[139],"application":[142],"scenarios.":[143],"Furthermore,":[144],"provide":[146],"insights":[147],"into":[148],"existing":[149],"future":[152],"directions,":[154],"aiming":[155],"foster":[157],"innovation":[158],"toward":[159],"AGI.":[161]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}
