{"id":"https://openalex.org/W7134815302","doi":"https://doi.org/10.48550/arxiv.2603.08059","title":"ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning","display_name":"ImageEdit-R1: Boosting Multi-Agent Image Editing via Reinforcement Learning","publication_year":2026,"publication_date":"2026-03-09","ids":{"openalex":"https://openalex.org/W7134815302","doi":"https://doi.org/10.48550/arxiv.2603.08059"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2603.08059","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5128657300","display_name":"Yiran Zhao","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zhao, Yiran","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128671339","display_name":"Yaoqi Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Yaoqi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128665482","display_name":"Xiang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128658372","display_name":"Michael Qizhe Shieh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shieh, Michael Qizhe","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5128666394","display_name":"Trung Bui","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bui, Trung","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5128657300"],"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.4909999966621399,"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":0.4909999966621399,"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":0.06949999928474426,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.04320000112056732,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.8773999810218811},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7570000290870667},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.6920999884605408},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.49559998512268066},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48579999804496765},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.4496000111103058}],"concepts":[{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.8773999810218811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051000237464905},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7570000290870667},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.6920999884605408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5353000164031982},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.49559998512268066},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48579999804496765},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.4496000111103058},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36719998717308044},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.36320000886917114},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3224000036716461},{"id":"https://openalex.org/C2780310081","wikidata":"https://www.wikidata.org/wiki/Q1154312","display_name":"Video editing","level":2,"score":0.3154999911785126},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3125},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.31040000915527344},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.27790001034736633},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.27720001339912415},{"id":"https://openalex.org/C2780967703","wikidata":"https://www.wikidata.org/wiki/Q2571389","display_name":"Collaborative editing","level":2,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2603.08059","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},{"id":"doi:10.48550/arxiv.2603.08059","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2603.08059","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":"pmh:doi:10.48550/arxiv.2603.08059","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7721992135047913,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1],"rapid":[2],"advancement":[3],"of":[4,82,102],"commercial":[5],"multi-modal":[6],"models,":[7,33],"image":[8,26,69,137,169],"editing":[9,27,70,106,138,148,170],"has":[10],"garnered":[11],"significant":[12],"attention":[13],"due":[14],"to":[15,48,75,117],"its":[16],"widespread":[17],"applicability":[18],"in":[19],"daily":[20],"life.":[21],"Despite":[22],"impressive":[23],"progress,":[24],"existing":[25,124],"systems,":[28],"particularly":[29],"closed-source":[30,159],"or":[31,39,131],"proprietary":[32],"often":[34],"struggle":[35],"with":[36,55],"complex,":[37],"indirect,":[38],"multi-step":[40],"user":[41,98],"instructions.":[42],"These":[43],"limitations":[44],"hinder":[45],"their":[46,115],"ability":[47],"perform":[49],"nuanced,":[50],"context-aware":[51,147],"edits":[52],"that":[53,71,126,153],"align":[54],"human":[56],"intent.":[57],"In":[58],"this":[59],"work,":[60],"we":[61],"propose":[62],"ImageEdit-R1,":[63],"a":[64,80,140],"multi-agent":[65,164],"framework":[66,165],"for":[67,93],"intelligent":[68],"leverages":[72],"reinforcement":[73,112],"learning":[74,113],"coordinate":[76],"high-level":[77],"decision-making":[78,142],"across":[79,167],"set":[81],"specialized,":[83],"pretrained":[84],"vision-language":[85],"and":[86,108,120,146,162],"generative":[87],"agents.":[88],"Each":[89],"agent":[90],"is":[91],"responsible":[92],"distinct":[94],"capabilities--such":[95],"as":[96,139],"understanding":[97],"intent,":[99],"identifying":[100],"regions":[101],"interest,":[103],"selecting":[104],"appropriate":[105],"actions,":[107],"synthesizing":[109],"visual":[110],"content--while":[111],"governs":[114],"collaboration":[116],"ensure":[118],"coherent":[119],"goal-directed":[121],"behavior.":[122],"Unlike":[123],"approaches":[125],"rely":[127],"on":[128],"monolithic":[129],"models":[130,161],"hand-crafted":[132],"pipelines,":[133],"our":[134],"method":[135],"treats":[136],"sequential":[141],"problem,":[143],"enabling":[144],"dynamic":[145],"strategies.":[149],"Experimental":[150],"results":[151],"demonstrate":[152],"ImageEdit-R1":[154],"consistently":[155],"outperforms":[156],"both":[157],"individual":[158],"diffusion":[160],"alternative":[163],"baselines":[166],"multiple":[168],"datasets.":[171]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-03-11T00:00:00"}
