{"id":"https://openalex.org/W7204597527","doi":"https://doi.org/10.48550/arxiv.2608.26809","title":"Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning","display_name":"Thinking on Shots: Consistent Multi-Shot Video Editing with Agentic Reasoning","publication_year":2026,"publication_date":"2026-08-27","ids":{"openalex":"https://openalex.org/W7204597527","doi":"https://doi.org/10.48550/arxiv.2608.26809"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.26809","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26809","pdf_url":"https://arxiv.org/pdf/2608.26809","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/2608.26809","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129745700","display_name":"Chenyang Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Chenyang","raw_affiliation_strings":["VCIP , CS , Nankai University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP , CS , Nankai University ,","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036041413","display_name":"Fuchen Long","orcid":"https://orcid.org/0000-0003-0818-0985","observed_orcids":["https://orcid.org/0000-0003-0818-0985"]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long, Fuchen","raw_affiliation_strings":["Smart Creation Platform Department , Online Video BU , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Smart Creation Platform Department , Online Video BU , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133091311","display_name":"Binyuan Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Binyuan","raw_affiliation_strings":["Smart Creation Platform Department , Online Video BU , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Smart Creation Platform Department , Online Video BU , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014852570","display_name":"Xinlong Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Sun, Xinlong","raw_affiliation_strings":["Smart Creation Platform Department , Online Video BU , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Smart Creation Platform Department , Online Video BU , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146905202","display_name":"Xi Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I2250653659","display_name":"Tencent (China)","ror":"https://ror.org/00hhjss72","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250653659"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Xi","raw_affiliation_strings":["Smart Creation Platform Department , Online Video BU , Tencent"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Smart Creation Platform Department , Online Video BU , Tencent","institution_ids":["https://openalex.org/I2250653659"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119712841","display_name":"Chun-Le Guo","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guo, Chun-Le","raw_affiliation_strings":["VCIP , CS , Nankai University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP , CS , Nankai University ,","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125547964","display_name":"Chongyi Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Chongyi","raw_affiliation_strings":["VCIP , CS , Nankai University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP , CS , Nankai University ,","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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":0.9404000043869019,"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":0.9404000043869019,"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":0.03830000013113022,"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/T11439","display_name":"Video Analysis and Summarization","score":0.015399999916553497,"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/agentic-reasoning","display_name":"agentic reasoning","score":0.6899999976158142},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7110000252723694},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.9959999918937683},{"id":"https://openalex.org/keywords/video-chunking","display_name":"video chunking","score":0.7120000123977661}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8575000166893005},{"id":"https://openalex.org/C203357204","wikidata":"https://www.wikidata.org/wiki/Q1089605","display_name":"Chunking (psychology)","level":2,"score":0.6216999888420105},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.5311999917030334},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.49480000138282776},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.47440001368522644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4666000008583069},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.4652000069618225},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4618000090122223},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4106999933719635},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.3919000029563904},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.3553999960422516},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33009999990463257},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3296000063419342},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.3140000104904175},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.259799987077713}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.26809","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26809","pdf_url":"https://arxiv.org/pdf/2608.26809","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.2608.26809","doi":"https://doi.org/10.48550/arxiv.2608.26809","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.26809","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:2608.26809","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.26809","pdf_url":"https://arxiv.org/pdf/2608.26809","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":[{"id":"https://openalex.org/F4320316083","display_name":"Tencent","ror":"https://ror.org/00hhjss72"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204597527.pdf","grobid_xml":"https://content.openalex.org/works/W7204597527.grobid-xml"},"referenced_works_count":11,"referenced_works":["https://openalex.org/W4289785045","https://openalex.org/W4390041933","https://openalex.org/W4409092337","https://openalex.org/W4416191636","https://openalex.org/W4417126972","https://openalex.org/W7101984403","https://openalex.org/W7154629535","https://openalex.org/W7161696487","https://openalex.org/W7161736846","https://openalex.org/W7164024852","https://openalex.org/W7203735005"],"related_works":["https://openalex.org/W7165662552","https://openalex.org/W6979324882","https://openalex.org/W4402979447","https://openalex.org/W4417300583","https://openalex.org/W7212069961","https://openalex.org/W7215078243","https://openalex.org/W7204216675","https://openalex.org/W7171630113","https://openalex.org/W7147719459","https://openalex.org/W7083306376"],"abstract_inverted_index":{"While":[0],"generative":[1],"AI":[2],"has":[3],"significantly":[4],"advanced":[5],"video":[6,16,107],"editing,":[7],"existing":[8,163],"methods":[9],"primarily":[10],"focus":[11],"on":[12,75],"single-shot":[13],"or":[14],"short":[15],"clips.":[17],"Editing":[18,56,67],"long":[19],"videos":[20],"with":[21],"multiple":[22],"instructions":[23],"remains":[24],"a":[25],"formidable":[26],"challenge.":[27],"Naive":[28],"chunking":[29],"strategies,":[30],"e.g.,":[31],"fixed-duration":[32],"segmentation,":[33],"often":[34],"lead":[35],"to":[36,104,114,148],"entity":[37,139],"fragmentation,":[38],"severe":[39],"editing":[40,89,154,172,176],"hallucinations,":[41,173],"and":[42,73,100,109,136,178],"disrupted":[43],"temporal":[44],"continuity.":[45],"To":[46,79],"bridge":[47],"this":[48,117],"gap,":[49],"we":[50,85,119],"introduce":[51,86],"the":[52,93,150,153],"Multi-Instruction":[53,70],"Multi-Shot":[54],"Long-Video":[55],"(MMLVE)":[57],"task,":[58,118],"which":[59,122],"is":[60,123],"structured":[61],"around":[62],"three":[63,82],"core":[64],"objectives:":[65],"Cross-Shot":[66],"Consistency":[68],"(CSEC),":[69],"Decoupling":[71],"(MID),":[72],"Zero-Destruction":[74],"Spatiotemporal":[76],"Structure":[77],"(ZDSS).":[78],"tackle":[80],"these":[81],"unique":[83],"challenges,":[84],"an":[87,124],"agentic":[88],"framework":[90],"that":[91,159],"leverages":[92],"synergy":[94],"of":[95,152],"Large":[96],"Language":[97],"Models":[98,102],"(LLMs)":[99],"Vision-Language":[101],"(VLMs)":[103],"achieve":[105],"shot-level":[106],"decoupling":[108],"precise":[110],"instruction":[111],"parsing.":[112],"Furthermore,":[113],"comprehensively":[115],"evaluate":[116],"construct":[120],"MMLVE-Bench,":[121],"MMLVE-focused":[125,142],"dataset":[126],"characterized":[127],"by":[128],"complex":[129],"real-world":[130],"spatiotemporal":[131,181],"dynamics,":[132],"high-density":[133],"heterogeneous":[134],"instructions,":[135],"sparse,":[137],"random":[138],"distributions.":[140],"Three":[141],"evaluation":[143],"metrics":[144],"are":[145],"further":[146],"exploited":[147],"assess":[149],"quality":[151],"results.":[155],"Extensive":[156],"experiments":[157],"demonstrate":[158],"our":[160],"MMLVE-Agent":[161],"outperforms":[162],"closed-source":[164],"SOTA":[165],"approaches":[166],"(e.g.,":[167],"Seedance":[168],"2.0),":[169],"successfully":[170],"eliminating":[171],"preserving":[174],"cross-shot":[175],"consistency,":[177],"attaining":[179],"seamless":[180],"transitions.":[182]},"counts_by_year":[{"year":2026,"cited_by_count":3}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-29T00:00:00"}