{"id":"https://openalex.org/W7214974343","doi":"https://doi.org/10.48550/arxiv.2609.37407","title":"Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation","display_name":"Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation","publication_year":2026,"publication_date":"2026-09-29","ids":{"openalex":"https://openalex.org/W7214974343","doi":"https://doi.org/10.48550/arxiv.2609.37407"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.37407","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37407","pdf_url":"https://arxiv.org/pdf/2609.37407","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.37407","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5042966060","display_name":"Xianghan Wei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei, Xianghan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153579315","display_name":"Xiaoda Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xiaoda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153606482","display_name":"Zhi Wang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zhi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072407605","display_name":"An Pan","orcid":"https://orcid.org/0000-0001-7710-3815","observed_orcids":["https://orcid.org/0000-0001-7710-3815"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pan, An","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081992105","display_name":"Daoan Zhang","orcid":"https://orcid.org/0000-0002-6959-165X","observed_orcids":["https://orcid.org/0000-0002-6959-165X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Daoan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035400091","display_name":"Huayi Zhang","orcid":"https://orcid.org/0009-0008-8547-2483","observed_orcids":["https://orcid.org/0009-0008-8547-2483"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Huayi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153631913","display_name":"Yan Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153665217","display_name":"Wei Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137659354","display_name":"Zishun Liao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liao, Zishun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5031568527","display_name":"Jianwen Lou","orcid":"https://orcid.org/0000-0001-8403-8046","observed_orcids":["https://orcid.org/0000-0001-8403-8046"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lou, Jianwen","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":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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9955999851226807,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9955999851226807,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.004000000189989805,"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/T14254","display_name":"Digital Media and Visual Art","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/retrieval-augmented-prompting","display_name":"retrieval-augmented prompting","score":0.8960000276565552},{"id":"https://openalex.org/keywords/video-foundation-models","display_name":"video foundation models","score":0.7770000100135803},{"id":"https://openalex.org/keywords/text-to-video-generation","display_name":"text-to-video generation","score":0.48399999737739563}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8029000163078308},{"id":"https://openalex.org/C186644900","wikidata":"https://www.wikidata.org/wiki/Q194152","display_name":"Parsing","level":2,"score":0.5580999851226807},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5468999743461609},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5212000012397766},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5004000067710876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4991999864578247},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.44119998812675476},{"id":"https://openalex.org/C2778712577","wikidata":"https://www.wikidata.org/wiki/Q3505966","display_name":"Retraining","level":2,"score":0.436599999666214},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.42179998755455017},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3928000032901764},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.3889000117778778},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3824999928474426},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3490000069141388},{"id":"https://openalex.org/C200288055","wikidata":"https://www.wikidata.org/wiki/Q2621792","display_name":"Element (criminal law)","level":2,"score":0.3237000107765198},{"id":"https://openalex.org/C157657479","wikidata":"https://www.wikidata.org/wiki/Q2367247","display_name":"Closed captioning","level":3,"score":0.29420000314712524},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.2797999978065491},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2736999988555908},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.2680000066757202},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2644999921321869},{"id":"https://openalex.org/C75553542","wikidata":"https://www.wikidata.org/wiki/Q178161","display_name":"A priori and a posteriori","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.26190000772476196},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.25870001316070557},{"id":"https://openalex.org/C105842133","wikidata":"https://www.wikidata.org/wiki/Q1899679","display_name":"Visual communication","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.37407","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37407","pdf_url":"https://arxiv.org/pdf/2609.37407","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2609.37407","doi":"https://doi.org/10.48550/arxiv.2609.37407","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.37407","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:2609.37407","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.37407","pdf_url":"https://arxiv.org/pdf/2609.37407","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214974343.pdf","grobid_xml":"https://content.openalex.org/works/W7214974343.grobid-xml"},"referenced_works_count":18,"referenced_works":["https://openalex.org/W4396814631","https://openalex.org/W4405055425","https://openalex.org/W4417284079","https://openalex.org/W4417307975","https://openalex.org/W4417531116","https://openalex.org/W6929617629","https://openalex.org/W7117143176","https://openalex.org/W7119504059","https://openalex.org/W7133312916","https://openalex.org/W7141643304","https://openalex.org/W7161263991","https://openalex.org/W7161686982","https://openalex.org/W7162487875","https://openalex.org/W7163184783","https://openalex.org/W7164024852","https://openalex.org/W7164826061","https://openalex.org/W7164924706","https://openalex.org/W7165658543"],"related_works":["https://openalex.org/W7119504059","https://openalex.org/W7220373354","https://openalex.org/W7111062764","https://openalex.org/W7117143176","https://openalex.org/W7117721277","https://openalex.org/W7164826061","https://openalex.org/W7215736923","https://openalex.org/W7214774669","https://openalex.org/W7221802778","https://openalex.org/W7171849871"],"abstract_inverted_index":{"While":[0],"recent":[1],"video":[2,12,107,198],"foundation":[3],"models":[4,120],"excel":[5],"at":[6],"generating":[7],"high-quality":[8],"short":[9],"videos,":[10],"long-form":[11,106],"generation":[13,108,217],"remains":[14],"a":[15,19,36,91,135,192],"critical":[16],"challenge,":[17],"where":[18],"major":[20],"bottleneck":[21],"lies":[22],"in":[23,230],"conditioning":[24,104,205],"independently":[25],"generated":[26],"shots":[27,44],"to":[28,65,99,157],"preserve":[29],"consistent":[30],"characters,":[31,142],"scenes,":[32,144],"and":[33,102,145,186,211,226,233],"objects":[34],"throughout":[35],"story.":[37],"Existing":[38],"training-free":[39],"approaches":[40],"typically":[41],"condition":[42],"target":[43,75,127],"using":[45],"retrieved":[46,181],"historical":[47,97,177],"visuals.":[48],"However,":[49],"these":[50,155],"references":[51,98,170],"often":[52],"suffer":[53],"from":[54],"severe":[55],"informational":[56],"mismatch,":[57],"either":[58],"introducing":[59],"irrelevant":[60],"contextual":[61],"redundancy":[62],"or":[63,111],"failing":[64],"provide":[66],"the":[67,74,113,121,131,163,180,196],"full":[68],"combination":[69],"of":[70,94],"required":[71,124,164],"elements":[72,123,156],"for":[73,105,195],"shot.":[76],"To":[77],"resolve":[78],"this,":[79],"we":[80],"present":[81],"Complementary":[82],"Retrieval-Augmented":[83],"Prompting,":[84],"an":[85],"agentic":[86],"framework":[87,118],"that":[88,140,171,219],"strategically":[89],"aggregates":[90],"compact":[92],"set":[93],"mutually":[95],"supportive":[96],"achieve":[100],"complete":[101],"targeted":[103],"without":[109],"retraining":[110],"modifying":[112],"underlying":[114],"generator.":[115,199],"Specifically,":[116],"our":[117,166,220],"explicitly":[119],"visual":[122,137,159],"by":[125,129,162],"each":[126],"shot":[128],"parsing":[130],"narrative":[132],"script":[133],"into":[134,191],"text-grounded":[136],"element":[138,184],"registry":[139],"tracks":[141],"objects,":[143],"their":[146],"shot-level":[147],"states.":[148],"A":[149],"VLM-annotated":[150],"keyframe":[151],"library":[152],"further":[153],"maps":[154],"past":[158],"observations.":[160],"Guided":[161],"elements,":[165],"agent":[167],"retrieves":[168],"complementary":[169],"maximize":[172],"target-element":[173],"coverage":[174],"while":[175,206],"minimizing":[176],"noise.":[178],"Finally,":[179],"references,":[182],"structured":[183],"states,":[185],"grounding":[187],"instructions":[188],"are":[189],"assembled":[190],"unified":[193],"prompt":[194],"frozen":[197],"This":[200],"element-aware":[201],"process":[202],"provides":[203],"comprehensive":[204],"remaining":[207],"fully":[208],"interpretable.":[209],"Quantitative":[210],"qualitative":[212],"evaluations":[213],"on":[214],"multi-shot":[215],"story":[216],"demonstrate":[218],"method":[221],"consistently":[222],"outperforms":[223],"recent-frame,":[224],"memory-based,":[225],"entity-level":[227],"retrieval":[228],"baselines":[229],"cross-shot":[231],"consistency":[232],"text-controllability.":[234]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-10-01T00:00:00"}