{"id":"https://openalex.org/W7154956070","doi":"https://doi.org/10.48550/arxiv.2604.15917","title":"Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions","display_name":"Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions","publication_year":2026,"publication_date":"2026-04-17","ids":{"openalex":"https://openalex.org/W7154956070","doi":"https://doi.org/10.48550/arxiv.2604.15917"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.15917","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15917","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":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.15917","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134025986","display_name":"Bo Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134036424","display_name":"Kairui Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Kairui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134055320","display_name":"Runnan Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Runnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134060334","display_name":"Haiyang Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Haiyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134087480","display_name":"Pengshan Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Pengshan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134022911","display_name":"Huan Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Huan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134063176","display_name":"Kun Gai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gai, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134043120","display_name":"Yixin Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Yixin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5134056591","display_name":"Wei Ji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ji, Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":9,"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":0.35600000619888306,"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":0.35600000619888306,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.2125999927520752,"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/T10533","display_name":"Teaching and Learning Programming","score":0.023499999195337296,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/image-editing","display_name":"Image editing","score":0.9024999737739563},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.7922999858856201},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5586000084877014},{"id":"https://openalex.org/keywords/frame","display_name":"Frame (networking)","score":0.5465999841690063},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4846000075340271},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.48249998688697815},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4275999963283539}],"concepts":[{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.9024999737739563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.83160001039505},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7922999858856201},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5586000084877014},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.5465999841690063},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4961000084877014},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4846000075340271},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4275999963283539},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4120999872684479},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36890000104904175},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.34119999408721924},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C197115733","wikidata":"https://www.wikidata.org/wiki/Q1003136","display_name":"Forcing (mathematics)","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C87829876","wikidata":"https://www.wikidata.org/wiki/Q648877","display_name":"Post-production","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.15917","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15917","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":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.15917","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.15917","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":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Instruction":[0],"guided":[1],"image":[2,62],"editing":[3,43,63,79,129,171],"has":[4],"advanced":[5],"substantially":[6],"with":[7,142],"recent":[8],"generative":[9],"models,":[10],"yet":[11],"it":[12],"still":[13],"fails":[14],"to":[15,90,173],"produce":[16],"reliable":[17],"results":[18,150],"across":[19,127],"many":[20],"seemingly":[21],"simple":[22],"cases.":[23,148],"We":[24],"observe":[25],"that":[26,77,101,152,162],"a":[27,66,97,108,156],"large":[28,144],"portion":[29],"of":[30,99,178],"these":[31],"failures":[32,64],"stem":[33],"not":[34],"from":[35,40],"insufficient":[36],"model":[37],"capacity,":[38],"but":[39,158],"poorly":[41],"formulated":[42],"tasks,":[44],"such":[45,131],"as":[46,65,132],"those":[47],"involving":[48],"small":[49],"targets,":[50],"implicit":[51],"spatial":[52],"relations,":[53],"or":[54],"under-specified":[55],"instructions.":[56],"In":[57],"this":[58],"work,":[59],"we":[60],"frame":[61],"task":[67,74,153],"formulation":[68],"problem":[69],"and":[70,105,115,125,136,161],"propose":[71],"an":[72],"adaptive":[73],"reformulation":[75,154],"framework":[76],"improves":[78],"performance":[80],"without":[81],"modifying":[82],"the":[83,92,174],"underlying":[84],"model.":[85],"Our":[86],"key":[87],"idea":[88],"is":[89,155],"transform":[91],"original":[93],"image-instruction":[94],"pair":[95],"into":[96],"sequence":[98],"operations":[100],"are":[102],"dynamically":[103],"determined":[104],"executed":[106],"by":[107,168],"MLLM":[109],"agent":[110],"through":[111],"analysis,":[112],"routing,":[113],"reformulation,":[114],"feedback-driven":[116],"refinement.":[117],"Experiments":[118],"on":[119,146],"multiple":[120],"benchmarks,":[121],"including":[122],"ImgEdit,":[123],"PICA,":[124],"RePlan,":[126],"diverse":[128],"backbones":[130],"Qwen":[133],"Image":[134],"Edit":[135],"Nano":[137],"Banana,":[138],"show":[139],"consistent":[140],"improvements,":[141],"especially":[143],"gains":[145,164],"challenging":[147],"These":[149],"suggest":[151],"critical":[157],"underexplored":[159],"factor,":[160],"substantial":[163],"can":[165],"be":[166],"achieved":[167],"better":[169],"matching":[170],"tasks":[172],"effective":[175],"operating":[176],"regime":[177],"existing":[179],"models.":[180]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-21T00:00:00"}