{"id":"https://openalex.org/W7160880599","doi":"https://doi.org/10.48550/arxiv.2605.07457","title":"EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement","display_name":"EditRefiner: A Human-Aligned Agentic Framework for Image Editing Refinement","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160880599","doi":"https://doi.org/10.48550/arxiv.2605.07457"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07457","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07457","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":null,"license_id":null,"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.2605.07457","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135905001","display_name":"Zitong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zitong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135869321","display_name":"Huiyu Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Huiyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133334845","display_name":"Yifei Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Yifei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135902142","display_name":"Mingda Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Mingda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135833506","display_name":"Sijing Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Sijing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135879920","display_name":"Xiongkuo Min","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Min, Xiongkuo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135836639","display_name":"Tianyi Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Tianyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135861085","display_name":"Jian Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042627504","display_name":"Shusong Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Shusong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135838764","display_name":"Jinwei Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jinwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135856463","display_name":"Bo Li","orcid":"https://orcid.org/0009-0001-8108-4765"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Bo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135833169","display_name":"Guangtao Zhai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Guangtao","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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.4512999951839447,"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":0.4512999951839447,"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":0.1031000018119812,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.03709999844431877,"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/perception","display_name":"Perception","score":0.6409000158309937},{"id":"https://openalex.org/keywords/image-editing","display_name":"Image editing","score":0.6244999766349792},{"id":"https://openalex.org/keywords/iterative-refinement","display_name":"Iterative refinement","score":0.586899995803833},{"id":"https://openalex.org/keywords/artifact","display_name":"Artifact (error)","score":0.5600000023841858},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5425999760627747},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5368000268936157},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.48410001397132874},{"id":"https://openalex.org/keywords/distortion","display_name":"Distortion (music)","score":0.45590001344680786}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8051999807357788},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6409000158309937},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.6244999766349792},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6093999743461609},{"id":"https://openalex.org/C2779982483","wikidata":"https://www.wikidata.org/wiki/Q6094420","display_name":"Iterative refinement","level":2,"score":0.586899995803833},{"id":"https://openalex.org/C2779010991","wikidata":"https://www.wikidata.org/wiki/Q2720909","display_name":"Artifact (error)","level":2,"score":0.5600000023841858},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5425999760627747},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5368000268936157},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.48410001397132874},{"id":"https://openalex.org/C126780896","wikidata":"https://www.wikidata.org/wiki/Q899871","display_name":"Distortion (music)","level":4,"score":0.45590001344680786},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4544999897480011},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.37560001015663147},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.3596000075340271},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3441999852657318},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3237000107765198},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C160086991","wikidata":"https://www.wikidata.org/wiki/Q5939193","display_name":"Human visual system model","level":3,"score":0.29840001463890076},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.2856000065803528},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2816999852657318},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.26339998841285706},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.2533999979496002}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07457","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07457","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.07457","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07457","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":null,"license_id":null,"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":{"Recent":[0],"text-guided":[1],"image":[2,191,230],"editing":[3,82,91,151],"(TIE)":[4],"models":[5,40,79],"have":[6],"made":[7],"remarkable":[8],"progress,":[9],"yet":[10],"edited":[11,70],"images":[12,75],"still":[13],"frequently":[14],"suffer":[15],"from":[16,76],"fine-grained":[17,66],"issues":[18],"such":[19],"as":[20,131],"unnatural":[21],"objects,":[22],"lighting":[23],"mismatch,":[24],"and":[25,51,89,99,111,123,150,178,182,192,217,227],"unexpected":[26],"changes.":[27],"Existing":[28],"refinement":[29],"approaches":[30],"either":[31],"rely":[32],"on":[33,115,197],"costly":[34],"iterative":[35],"regeneration":[36],"or":[37],"employ":[38],"vision-language":[39],"(VLMs)":[41],"with":[42],"weak":[43],"spatial":[44],"grounding,":[45],"often":[46],"resulting":[47],"in":[48,212],"semantic":[49],"drift":[50],"unreliable":[52],"local":[53],"corrections.":[54],"To":[55],"address":[56],"these":[57,159],"limitations,":[58],"we":[59,117,137],"first":[60],"construct":[61],"EditFHF-15K,":[62,116],"a":[63,120,132,140,154,222],"dataset":[64],"of":[65,148],"human":[67,218],"feedback":[68],"for":[69,225],"images,":[71],"comprising":[72],"(1)":[73,139],"15K":[74],"12":[77],"TIE":[78],"spanning":[80],"43":[81],"tasks,":[83],"(2)":[84,153],"60K":[85],"annotated":[86],"artifact":[87],"regions":[88],"80K":[90],"failure":[92],"regions,":[93],"each":[94],"accompanied":[95],"by":[96],"textual":[97],"reasoning,":[98],"(3)":[100,167],"45K":[101],"mean":[102],"opinion":[103],"scores":[104],"(MOSs)":[105],"assessing":[106],"perceptual":[107,160],"quality,":[108],"instruction":[109],"following,":[110],"visual":[112],"consistency.":[113],"Based":[114],"propose":[118],"EditRefiner,":[119],"hierarchical,":[121],"interpretable,":[122],"human-aligned":[124,164],"agentic":[125],"framework":[126],"that":[127,143,157,171,187,206],"reformulates":[128],"post-editing":[129],"correction":[130],"human-like":[133],"perception-reasoning-action-evaluation":[134],"loop.":[135],"Specifically,":[136],"introduce:":[138],"perception":[141,219],"agent":[142,156,170,186,196],"detects":[144],"contextual":[145],"saliency":[146],"maps":[147],"artifacts":[149],"failures,":[152],"reasoning":[155,174],"interprets":[158],"cues":[161],"to":[162,176],"perform":[163],"diagnostic":[165],"inference,":[166],"an":[168,184],"action":[169,195],"uses":[172],"the":[173,189,194],"output":[175],"plan":[177],"execute":[179],"localized":[180],"re-editing,":[181],"(4)":[183],"evaluation":[185],"assesses":[188],"re-edited":[190],"guides":[193],"whether":[198],"further":[199],"refinements":[200],"are":[201],"required.":[202],"Extensive":[203],"experiments":[204],"demonstrate":[205],"EditRefiner":[207],"consistently":[208],"outperforms":[209],"state-of-the-art":[210],"methods":[211],"distortion":[213],"localization,":[214],"diagnose":[215],"accuracy":[216],"alignment,":[220],"establishing":[221],"new":[223],"paradigm":[224],"self-corrective":[226],"perceptually":[228],"reliable":[229],"editing.":[231],"The":[232],"code":[233],"is":[234],"available":[235],"at":[236],"https://github.com/IntMeGroup/EditRefiner.":[237]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-12T00:00:00"}