{"id":"https://openalex.org/W7143362698","doi":"https://doi.org/10.48550/arxiv.2603.26348","title":"Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification","display_name":"Reflect to Inform: Boosting Multimodal Reasoning via Information-Gain-Driven Verification","publication_year":2026,"publication_date":"2026-03-27","ids":{"openalex":"https://openalex.org/W7143362698","doi":"https://doi.org/10.48550/arxiv.2603.26348"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.26348","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26348","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.2603.26348","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130913852","display_name":"Shuai Lv","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130911115","display_name":"Chang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Chang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130917601","display_name":"Feng Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Feng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022783425","display_name":"Yujie Yuan","orcid":"https://orcid.org/0000-0002-9114-4979"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuan, Yujie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041431476","display_name":"Aojun Zhou","orcid":"https://orcid.org/0000-0002-4742-8624"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Aojun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130975962","display_name":"Kui Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130925472","display_name":"Xi Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5130991546","display_name":"Yangqiu Song","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Yangqiu","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":0.9609000086784363,"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":0.9609000086784363,"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":0.005100000184029341,"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":0.003100000089034438,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.6621999740600586},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.5249999761581421},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.47679999470710754},{"id":"https://openalex.org/keywords/introspection","display_name":"Introspection","score":0.3862000107765198},{"id":"https://openalex.org/keywords/visual-perception","display_name":"Visual perception","score":0.35929998755455017},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.34200000762939453},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3346000015735626},{"id":"https://openalex.org/keywords/opportunistic-reasoning","display_name":"Opportunistic reasoning","score":0.3070000112056732},{"id":"https://openalex.org/keywords/reasoning-system","display_name":"Reasoning system","score":0.2957000136375427}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789900004863739},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.6621999740600586},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6222000122070312},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.5249999761581421},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.47679999470710754},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4564000070095062},{"id":"https://openalex.org/C129671850","wikidata":"https://www.wikidata.org/wiki/Q210501","display_name":"Introspection","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.35929998755455017},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.34200000762939453},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3346000015735626},{"id":"https://openalex.org/C86827895","wikidata":"https://www.wikidata.org/wiki/Q7098582","display_name":"Opportunistic reasoning","level":4,"score":0.3070000112056732},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.2957000136375427},{"id":"https://openalex.org/C195344581","wikidata":"https://www.wikidata.org/wiki/Q2555318","display_name":"Automated reasoning","level":2,"score":0.29249998927116394},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.28369998931884766},{"id":"https://openalex.org/C37335422","wikidata":"https://www.wikidata.org/wiki/Q6888134","display_name":"Model-based reasoning","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.27469998598098755},{"id":"https://openalex.org/C2780103172","wikidata":"https://www.wikidata.org/wiki/Q1309721","display_name":"Visual Objects","level":3,"score":0.2676999866962433},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.266400009393692},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.25999999046325684},{"id":"https://openalex.org/C2780660688","wikidata":"https://www.wikidata.org/wiki/Q25052564","display_name":"Multimodal learning","level":2,"score":0.2597000002861023},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.2563999891281128},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2515000104904175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.26348","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26348","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.2603.26348","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.26348","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":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.652224600315094}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Multimodal":[0],"Large":[1],"Language":[2],"Models":[3],"(MLLMs)":[4],"achieve":[5],"strong":[6],"multimodal":[7,127],"reasoning":[8,40,89,134],"performance,":[9],"yet":[10],"we":[11,48,71],"identify":[12],"a":[13,53,76,100],"recurring":[14],"failure":[15],"mode":[16],"in":[17,38,144],"long-form":[18],"generation:":[19],"as":[20],"outputs":[21],"grow":[22],"longer,":[23],"models":[24],"progressively":[25],"drift":[26],"away":[27],"from":[28,99],"image":[29],"evidence":[30],"and":[31,41,136],"fall":[32],"back":[33],"on":[34,45],"textual":[35],"priors,":[36],"resulting":[37],"ungrounded":[39],"hallucinations.":[42],"Interestingly,":[43],"Based":[44],"attention":[46],"analysis,":[47],"find":[49],"that":[50,60,80,130],"MLLMs":[51,82],"have":[52],"latent":[54],"capability":[55],"for":[56],"late-stage":[57],"visual":[58,86,92,97,117],"verification":[59],"is":[61,148],"present":[62],"but":[63],"not":[64],"consistently":[65,132],"activated.":[66],"Motivated":[67],"by":[68,107],"this":[69],"observation,":[70],"propose":[72],"Visual":[73],"Re-Examination":[74],"(VRE),":[75],"self-evolving":[77],"training":[78],"framework":[79],"enables":[81],"to":[83,112],"autonomously":[84],"perform":[85],"introspection":[87],"during":[88],"without":[90],"additional":[91],"inputs.":[93],"Rather":[94],"than":[95],"distilling":[96],"capabilities":[98],"stronger":[101],"teacher,":[102],"VRE":[103,131],"promotes":[104],"iterative":[105],"self-improvement":[106],"leveraging":[108],"the":[109],"model":[110],"itself":[111],"generate":[113],"reflection":[114],"traces,":[115],"making":[116],"information":[118,121],"actionable":[119],"through":[120],"gain.":[122],"Extensive":[123],"experiments":[124],"across":[125],"diverse":[126],"benchmarks":[128],"demonstrate":[129],"improves":[133],"accuracy":[135],"perceptual":[137],"reliability,":[138],"while":[139],"substantially":[140],"reducing":[141],"hallucinations,":[142],"especially":[143],"long-chain":[145],"settings.":[146],"Code":[147],"available":[149],"at":[150],"https://github.com/Xiaobu-USTC/VRE.":[151]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-31T00:00:00"}