{"id":"https://openalex.org/W7165667220","doi":"https://doi.org/10.48550/arxiv.2606.22565","title":"Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do","display_name":"Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do","publication_year":2026,"publication_date":"2026-06-21","ids":{"openalex":"https://openalex.org/W7165667220","doi":"https://doi.org/10.48550/arxiv.2606.22565"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22565","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22565","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.22565","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139168300","display_name":"Zhuoran Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Zhuoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138457134","display_name":"Kejian Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Kejian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139159963","display_name":"Hongbang Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Hongbang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139182855","display_name":"Yupu Hao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Yupu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139175948","display_name":"Pengfei Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Pengfei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139184274","display_name":"Yubo Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Yubo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139214012","display_name":"Kang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Kang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139191436","display_name":"Jun Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jun","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":0.7563999891281128,"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":0.7563999891281128,"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/T10656","display_name":"Child and Animal Learning Development","score":0.029400000348687172,"subfield":{"id":"https://openalex.org/subfields/3204","display_name":"Developmental and Educational Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11148","display_name":"Language, Metaphor, and Cognition","score":0.012799999676644802,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.7437999844551086},{"id":"https://openalex.org/keywords/analytic-reasoning","display_name":"Analytic reasoning","score":0.5658000111579895},{"id":"https://openalex.org/keywords/verbal-reasoning","display_name":"Verbal reasoning","score":0.5454999804496765},{"id":"https://openalex.org/keywords/introspection","display_name":"Introspection","score":0.5414000153541565},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5110999941825867},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/causal-reasoning","display_name":"Causal reasoning","score":0.42329999804496765},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.39559999108314514},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.37529999017715454}],"concepts":[{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.7437999844551086},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.5658000111579895},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5656999945640564},{"id":"https://openalex.org/C36964233","wikidata":"https://www.wikidata.org/wiki/Q7920942","display_name":"Verbal reasoning","level":3,"score":0.5454999804496765},{"id":"https://openalex.org/C129671850","wikidata":"https://www.wikidata.org/wiki/Q210501","display_name":"Introspection","level":2,"score":0.5414000153541565},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5110999941825867},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4578999876976013},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.42329999804496765},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.39559999108314514},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.3808000087738037},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.37599998712539673},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37529999017715454},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.36910000443458557},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.36629998683929443},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.3465999960899353},{"id":"https://openalex.org/C155911833","wikidata":"https://www.wikidata.org/wiki/Q3817354","display_name":"Spatial intelligence","level":2,"score":0.3393000066280365},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3382999897003174},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.3368000090122223},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C2780910867","wikidata":"https://www.wikidata.org/wiki/Q1952416","display_name":"Multimodality","level":2,"score":0.33009999990463257},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.32580000162124634},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.30079999566078186},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C183521366","wikidata":"https://www.wikidata.org/wiki/Q7256422","display_name":"Psychology of reasoning","level":4,"score":0.27570000290870667},{"id":"https://openalex.org/C166088908","wikidata":"https://www.wikidata.org/wiki/Q308495","display_name":"Abductive reasoning","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.25619998574256897},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2547999918460846}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22565","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22565","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.22565","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22565","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":"Preprint"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.4238966703414917}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Chain-of-Thought":[0,42],"(CoT)":[1],"has":[2],"become":[3],"a":[4,85,169,179],"standard":[5],"method":[6],"for":[7,126,172],"improving":[8],"reasoning":[9,43,64,73,127,143,158,167,221],"capabilities":[10],"in":[11,23,115],"large":[12],"language":[13],"models":[14,70,144,177],"(LLMs)":[15],"by":[16],"eliciting":[17],"step-by-step":[18],"thinking,":[19],"but":[20],"its":[21],"effectiveness":[22],"multimodal":[24,41,59,142,174,203],"tasks":[25,60,128],"remains":[26,168],"unclear.":[27],"In":[28,121],"this":[29,54],"paper,":[30],"we":[31,56],"aim":[32],"to":[33,107,137,153,214],"systematically":[34],"investigate":[35],"the":[36,95,160,212,220],"key":[37,170],"question:":[38],"What":[39],"can":[40,105],"do,":[44],"and":[45,47,63,71,88,118,132,189],"where":[46,185],"why":[48],"does":[49],"it":[50,123,210],"fall":[51],"short?":[52],"To":[53],"end,":[55],"evaluate":[57],"12":[58],"across":[61],"perception":[62,102],"categories":[65],"using":[66],"both":[67],"14":[68],"non-reasoning":[69],"8":[72],"models.":[74],"Our":[75],"analysis":[76],"reveals":[77],"several":[78],"important":[79],"findings:":[80],"(1)":[81],"CoT":[82,104,204],"is":[83],"not":[84],"free":[86],"lunch":[87],"should":[89],"be":[90],"used":[91],"selectively":[92],"depending":[93],"on":[94,156],"specific":[96],"requirements":[97],"of":[98,162],"each":[99],"task.":[100],"For":[101],"tasks,":[103],"lead":[106],"undesirable":[108],"side":[109],"effects,":[110],"such":[111],"as":[112,176],"reduced":[113],"performance":[114],"visual":[116,194,217],"grounding":[117],"object":[119],"counting.":[120],"contrast,":[122],"proves":[124],"effective":[125],"involving":[129],"mathematical,":[130],"scientific,":[131],"multi-image":[133],"reasoning;":[134],"(2)":[135],"Compared":[136],"original":[138],"models,":[139],"existing":[140],"open-source":[141],"often":[145],"yield":[146],"only":[147],"marginal":[148],"overall":[149],"improvements,":[150],"possibly":[151],"due":[152],"an":[154],"overemphasis":[155],"mathematical":[157],"at":[159],"expense":[161],"broader":[163],"capabilities;":[164],"(3)":[165],"Visual":[166],"bottleneck":[171],"current":[173],"CoT,":[175],"exhibit":[178],"Look":[180],"Light,":[181],"Think":[182],"Heavy":[183],"pattern":[184],"verbal":[186,206],"reflection":[187,195,207],"rises":[188],"falls":[190],"during":[191],"reasoning,":[192],"whereas":[193],"consistently":[196],"diminishes.":[197],"These":[198],"findings":[199],"suggest":[200],"that":[201],"while":[202],"handles":[205],"relatively":[208],"well,":[209],"lacks":[211],"ability":[213],"maintain":[215],"deep":[216],"introspection":[218],"throughout":[219],"process.":[222]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}