{"id":"https://openalex.org/W7147173078","doi":"https://doi.org/10.48550/arxiv.2603.29602","title":"IMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection","display_name":"IMAGAgent: Orchestrating Multi-Turn Image Editing via Constraint-Aware Planning and Reflection","publication_year":2026,"publication_date":"2026-02-12","ids":{"openalex":"https://openalex.org/W7147173078","doi":"https://doi.org/10.48550/arxiv.2603.29602"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2603.29602","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29602","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2603.29602","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shen, Fei","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Xie, Chengyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xie, Chengyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Wang, Lihong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lihong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Zhanyi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhanyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jiang, Xin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiang, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Du, Xiaoyu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Xiaoyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Tang, Jinhui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jinhui","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":0.41659998893737793,"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":0.41659998893737793,"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":0.14959999918937683,"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/T12377","display_name":"Digital Humanities and Scholarship","score":0.028300000354647636,"subfield":{"id":"https://openalex.org/subfields/1208","display_name":"Literature and Literary Theory"},"field":{"id":"https://openalex.org/fields/12","display_name":"Arts and Humanities"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/executable","display_name":"Executable","score":0.8446000218391418},{"id":"https://openalex.org/keywords/orchestration","display_name":"Orchestration","score":0.5964000225067139},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5652999877929688},{"id":"https://openalex.org/keywords/reflection","display_name":"Reflection (computer programming)","score":0.5569000244140625},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.5138999819755554},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.48809999227523804},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4065999984741211},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.40310001373291016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8572999835014343},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.8446000218391418},{"id":"https://openalex.org/C199168358","wikidata":"https://www.wikidata.org/wiki/Q3367000","display_name":"Orchestration","level":3,"score":0.5964000225067139},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5652999877929688},{"id":"https://openalex.org/C65682993","wikidata":"https://www.wikidata.org/wiki/Q1056451","display_name":"Reflection (computer programming)","level":2,"score":0.5569000244140625},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.5138999819755554},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.48809999227523804},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.44609999656677246},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.41839998960494995},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4065999984741211},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.40310001373291016},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.38760000467300415},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3862000107765198},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.3231000006198883},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.3098999857902527},{"id":"https://openalex.org/C96147967","wikidata":"https://www.wikidata.org/wiki/Q190686","display_name":"Subroutine","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.28049999475479126},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.26750001311302185},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2628999948501587}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2603.29602","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29602","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2603.29602","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.29602","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":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Existing":[0],"multi-turn":[1,32,50],"image":[2,51,145,168],"editing":[3,52,216],"paradigms":[4],"are":[5,23],"often":[6],"confined":[7],"to":[8,13,25,91,169,187,208],"isolated":[9],"single-step":[10],"execution.":[11],"Due":[12],"a":[14,49,57,74,81,87,99,154,160],"lack":[15],"of":[16,40,101,213],"context-awareness":[17],"and":[18,28,70,110,130,137,149,172,183,197,218],"closed-loop":[19,59],"feedback":[20,185],"mechanisms,":[21],"they":[22],"prone":[24],"error":[26],"accumulation":[27],"semantic":[29,108],"drift":[30],"during":[31],"interactions,":[33],"ultimately":[34],"resulting":[35],"in":[36,211],"severe":[37],"structural":[38],"distortion":[39],"the":[41,114,124,127,131,167,198],"generated":[42],"images.":[43],"For":[44],"that,":[45],"we":[46,78,152],"propose":[47],"\\textbf{IMAGAgent},":[48],"agent":[53],"framework":[54],"based":[55,122],"on":[56,123,193],"\"plan-execute-reflect\"":[58],"mechanism":[60,158],"that":[61,85,202],"achieves":[62,204],"deep":[63],"synergy":[64],"among":[65,140],"instruction":[66,214],"parsing,":[67],"tool":[68],"scheduling,":[69],"adaptive":[71,135],"correction":[72],"within":[73],"unified":[75],"pipeline.":[76],"Specifically,":[77],"first":[79],"present":[80],"constraint-aware":[82],"planning":[83],"module":[84,117],"leverages":[86],"vision-language":[88],"model":[89,164],"(VLM)":[90],"precisely":[92],"decompose":[93],"complex":[94],"natural":[95],"language":[96,163],"instructions":[97],"into":[98,176],"series":[100],"executable":[102],"sub-tasks,":[103],"governed":[104],"by":[105],"target":[106],"singularity,":[107],"atomicity,":[109],"visual":[111],"perceptibility.":[112],"Then,":[113],"tool-chain":[115],"orchestration":[116],"dynamically":[118],"constructs":[119],"execution":[120],"paths":[121],"current":[125,128],"image,":[126],"sub-task,":[129],"historical":[132],"context,":[133],"enabling":[134],"scheduling":[136],"collaborative":[138,156],"operation":[139,142],"heterogeneous":[141],"models":[143],"covering":[144],"retrieval,":[146],"segmentation,":[147],"detection,":[148],"editing.":[150],"Finally,":[151],"devise":[153],"multi-expert":[155],"reflection":[157],"where":[159],"central":[161],"large":[162],"(LLM)":[165],"receives":[166],"be":[170],"edited":[171],"synthesizes":[173],"VLM":[174],"critiques":[175],"holistic":[177],"feedback,":[178],"simultaneously":[179],"triggering":[180],"fine-grained":[181],"self-correction":[182],"recording":[184],"outcomes":[186],"optimize":[188],"future":[189],"decisions.":[190],"Extensive":[191],"experiments":[192],"our":[194],"constructed":[195],"\\textbf{MTEditBench}":[196],"MagicBrush":[199],"dataset":[200],"demonstrate":[201],"IMAGAgent":[203],"performance":[205],"significantly":[206],"superior":[207],"existing":[209],"methods":[210],"terms":[212],"consistency,":[215],"precision,":[217],"overall":[219],"quality.":[220],"The":[221],"code":[222],"is":[223],"available":[224],"at":[225],"https://github.com/hackermmzz/IMAGAgent.git.":[226]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-03-11T00:00:00"}