{"id":"https://openalex.org/W7126095086","doi":"https://doi.org/10.48550/arxiv.2601.20305","title":"Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models","display_name":"Endogenous Reprompting: Self-Evolving Cognitive Alignment for Unified Multimodal Models","publication_year":2026,"publication_date":"2026-01-28","ids":{"openalex":"https://openalex.org/W7126095086","doi":"https://doi.org/10.48550/arxiv.2601.20305"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.20305","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.20305","pdf_url":"https://arxiv.org/pdf/2601.20305","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2601.20305","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5121916011","display_name":"Zhenchen Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tang, Zhenchen","raw_affiliation_strings":["New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124181373","display_name":"Songlin Yang","orcid":"https://orcid.org/0000-0003-3403-376X","observed_orcids":["https://orcid.org/0000-0003-3403-376X"]},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yang, Songlin","raw_affiliation_strings":["MMLab @ HKUST , The Hong Kong University of Science and Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MMLab @ HKUST , The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124173903","display_name":"Zichuan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zichuan","raw_affiliation_strings":["New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124220568","display_name":"Bo Peng","orcid":"https://orcid.org/0000-0001-8133-3883","observed_orcids":["https://orcid.org/0000-0001-8133-3883"]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng, Bo","raw_affiliation_strings":["New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124292503","display_name":"Yang E. Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Yang","raw_affiliation_strings":["New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124261413","display_name":"Beibei Dong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong, Beibei","raw_affiliation_strings":["New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences","School of Artificial Intelligence , University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]},{"raw_affiliation_string":"School of Artificial Intelligence , University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124175232","display_name":"Jing Dong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong, Jing","raw_affiliation_strings":["New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition , Institute of Automation , Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/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"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.0,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/unified-multimodal-models","display_name":"unified multimodal models","score":0.9620000123977661},{"id":"https://openalex.org/keywords/cognitive-gap","display_name":"cognitive gap","score":0.5849999785423279},{"id":"https://openalex.org/keywords/generative-reasoning","display_name":"generative reasoning","score":0.675000011920929},{"id":"https://openalex.org/keywords/reinforcement-learning-with-verifiable-rewards","display_name":"reinforcement learning with verifiable rewards","score":0.8629999756813049},{"id":"https://openalex.org/keywords/curriculum-learning","display_name":"curriculum learning","score":0.6980000138282776},{"id":"https://openalex.org/keywords/self-assessment","display_name":"self-assessment","score":0.6140000224113464}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7265999913215637},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6266999840736389},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5953999757766724},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.593500018119812},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5800999999046326},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5005999803543091},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4812000095844269},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4535999894142151},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C40506919","wikidata":"https://www.wikidata.org/wiki/Q7452469","display_name":"Sequence learning","level":2,"score":0.33390000462532043},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.3109999895095825},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.2515000104904175}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.20305","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.20305","pdf_url":"https://arxiv.org/pdf/2601.20305","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.20305","doi":"https://doi.org/10.48550/arxiv.2601.20305","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.20305","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.20305","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.20305","pdf_url":"https://arxiv.org/pdf/2601.20305","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126095086.pdf","grobid_xml":"https://content.openalex.org/works/W7126095086.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415272862","https://openalex.org/W7161001380","https://openalex.org/W7106789511","https://openalex.org/W7134237298","https://openalex.org/W7166108033","https://openalex.org/W7160617442","https://openalex.org/W7140081368","https://openalex.org/W4416611615","https://openalex.org/W7212074684","https://openalex.org/W7154625525"],"abstract_inverted_index":{"Unified":[0],"Multimodal":[1],"Models":[2],"(UMMs)":[3],"exhibit":[4],"strong":[5],"understanding,":[6],"yet":[7],"this":[8,18,38,129],"capability":[9],"often":[10],"fails":[11],"to":[12,30,131],"effectively":[13],"guide":[14],"generation.":[15,67],"We":[16],"identify":[17],"as":[19],"a":[20,44,52,78,83,92,116],"Cognitive":[21],"Gap:":[22],"the":[23,26,48,107,133],"model":[24],"lacks":[25],"understanding":[27,50],"of":[28],"how":[29],"enhance":[31],"its":[32],"own":[33],"generation":[34,151],"process.":[35],"To":[36,68],"bridge":[37],"gap,":[39],"we":[40,71],"propose":[41],"Endogenous":[42],"Reprompting,":[43],"mechanism":[45],"that":[46,81,139],"transforms":[47],"model's":[49,108],"from":[51,91],"passive":[53],"encoding":[54],"process":[55],"into":[56],"an":[57],"explicit":[58],"generative":[59,134],"reasoning":[60,135],"step":[61],"by":[62],"generating":[63],"self-aligned":[64],"descriptors":[65],"during":[66],"achieve":[69],"this,":[70],"introduce":[72],"SEER":[73,140],"(Self-Evolving":[74],"Evaluator":[75],"and":[76,150],"Reprompter),":[77],"training":[79],"framework":[80],"establishes":[82],"two-stage":[84],"endogenous":[85,118],"loop":[86],"using":[87],"only":[88],"300":[89],"samples":[90],"compact":[93],"proxy":[94],"task,":[95],"Visual":[96],"Instruction":[97],"Elaboration.":[98],"First,":[99],"Reinforcement":[100,122],"Learning":[101,123],"with":[102,124],"Verifiable":[103],"Rewards":[104],"(RLVR)":[105],"activates":[106],"latent":[109],"evaluation":[110,146],"ability":[111],"via":[112],"curriculum":[113],"learning,":[114],"producing":[115],"high-fidelity":[117],"reward":[119],"signal.":[120],"Second,":[121],"Model-rewarded":[125],"Thinking":[126],"(RLMT)":[127],"leverages":[128],"signal":[130],"optimize":[132],"policy.":[136],"Experiments":[137],"show":[138],"consistently":[141],"outperforms":[142],"state-of-the-art":[143],"baselines":[144],"in":[145],"accuracy,":[147],"reprompting":[148],"efficiency,":[149],"quality,":[152],"without":[153],"sacrificing":[154],"general":[155],"multimodal":[156],"capabilities.":[157]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-01-30T00:00:00"}