{"id":"https://openalex.org/W7224834629","doi":"https://doi.org/10.48550/arxiv.2610.39664","title":"EditAgent: Rethinking Agentic Image Editing","display_name":"EditAgent: Rethinking Agentic Image Editing","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224834629","doi":"https://doi.org/10.48550/arxiv.2610.39664"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39664","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39664","pdf_url":"https://arxiv.org/pdf/2610.39664","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39664","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160179906","display_name":"Haiyang Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Haiyang","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160218060","display_name":"Tianyu Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Tianyu","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160237536","display_name":"Jialu Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li, Jialu","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030794078","display_name":"Jiteng Mu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mu, Jiteng","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005925571","display_name":"Yuanjun Xiong","orcid":"https://orcid.org/0000-0002-6391-4921","observed_orcids":["https://orcid.org/0000-0002-6391-4921"]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiong, Yuanjun","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160218305","display_name":"Jianming Zhang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhang, Jianming","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001760915","display_name":"Zhuowen Tu","orcid":"https://orcid.org/0000-0002-1900-2124","observed_orcids":["https://orcid.org/0000-0002-1900-2124"]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tu, Zhuowen","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160203475","display_name":"Mingze Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xu, Mingze","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1306409833"],"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":0.9907000064849854,"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":0.9907000064849854,"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":0.0052999998442828655,"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/T12357","display_name":"Digital Media Forensic Detection","score":0.0005000000237487257,"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/multi-step-reasoning","display_name":"multi-step reasoning","score":0.4860000014305115},{"id":"https://openalex.org/keywords/failure-handling","display_name":"failure management","score":0.4339999854564667},{"id":"https://openalex.org/keywords/reward-models","display_name":"reward models","score":0.8009999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8202999830245972},{"id":"https://openalex.org/C2780615836","wikidata":"https://www.wikidata.org/wiki/Q2471869","display_name":"USable","level":2,"score":0.6899999976158142},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6396999955177307},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.623199999332428},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.508400022983551},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.4733000099658966},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.41749998927116394},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.41119998693466187},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.36500000953674316},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.32690000534057617},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.287200003862381},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.28439998626708984},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.2766000032424927},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.2712000012397766},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.27000001072883606},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2615000009536743},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2526000142097473}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39664","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39664","pdf_url":"https://arxiv.org/pdf/2610.39664","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.39664","doi":"https://doi.org/10.48550/arxiv.2610.39664","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39664","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:2610.39664","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39664","pdf_url":"https://arxiv.org/pdf/2610.39664","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224834629.pdf","grobid_xml":"https://content.openalex.org/works/W7224834629.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7108230270","https://openalex.org/W7077888661","https://openalex.org/W7128624332","https://openalex.org/W7163988525","https://openalex.org/W7154956070","https://openalex.org/W7134815302","https://openalex.org/W4406356737","https://openalex.org/W7211890753","https://openalex.org/W7147173078","https://openalex.org/W7167063491"],"abstract_inverted_index":{"Agentic":[0],"image":[1],"editors":[2,100,156],"decompose":[3],"complex":[4],"requests":[5],"into":[6],"steps,":[7],"but":[8],"when":[9],"a":[10,24,66,109,163],"step":[11,97],"fails,":[12],"they":[13],"mostly":[14],"retry":[15],"with":[16],"the":[17,43,48,53,77,149],"same":[18],"narrow":[19],"set":[20],"of":[21,46,56,76,141],"tools":[22],"and":[23,52,79,101,104,127,160],"judge":[25,59,81,150],"that":[26,35],"scores":[27],"each":[28,96,107],"output":[29],"by":[30,40],"eye":[31],"directly.":[32],"We":[33,87],"argue":[34],"such":[36],"agents":[37],"are":[38,123],"bounded":[39],"two":[41,154],"spaces:":[42],"action":[44],"space":[45,55],"what":[47,57],"agent":[49],"can":[50,60],"do,":[51],"observation":[54],"its":[58],"see.":[61],"On":[62],"our":[63],"expert-annotated":[64],"benchmark,":[65],"general-purpose":[67],"editor":[68],"yields":[69],"no":[70,80,145],"usable":[71],"result":[72],"in":[73,125,129,139],"over":[74],"40%":[75],"cases,":[78],"is":[82],"reliable":[83],"across":[84],"edit":[85],"types.":[86],"present":[88],"EditAgent,":[89],"which":[90],"expands":[91],"both":[92],"spaces.":[93],"It":[94],"routes":[95],"to":[98,106,136],"general":[99],"specialized":[102],"methods,":[103],"attaches":[105],"candidate":[108],"verification":[110],"record.":[111],"With":[112],"these":[113],"records,":[114],"off-the-shelf":[115],"VLM":[116],"judges":[117],"outperform":[118],"finetuned":[119],"reward":[120],"models.":[121],"Candidates":[122],"generated":[124],"parallel":[126],"judged":[128],"one":[130],"listwise":[131],"call:":[132],"experts":[133],"prefer":[134],"this":[135],"sequential":[137],"refinement":[138],"78.5%":[140],"decided":[142],"comparisons,":[143],"at":[144],"more":[146],"than":[147],"half":[148],"calls.":[151],"EditAgent":[152],"improves":[153],"open-weight":[155],"on":[157],"three":[158],"benchmarks":[159],"serves":[161],"as":[162],"data":[164],"engine":[165],"for":[166],"training":[167],"stronger":[168],"editors.":[169]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-10-31T00:00:00"}