{"id":"https://openalex.org/W7163135862","doi":"https://doi.org/10.48550/arxiv.2606.00204","title":"APE: Agentic Prompt Enhancer for Image Generation and Editing","display_name":"APE: Agentic Prompt Enhancer for Image Generation and Editing","publication_year":2026,"publication_date":"2026-05-29","ids":{"openalex":"https://openalex.org/W7163135862","doi":"https://doi.org/10.48550/arxiv.2606.00204"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.00204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00204","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.2606.00204","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137625521","display_name":"Zijian Huang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Zijian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137702965","display_name":"Jay Zhangjie Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Jay Zhangjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137688713","display_name":"Zian Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Zian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043812968","display_name":"Tianshi Cao","orcid":"https://orcid.org/0000-0001-6579-6044"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Tianshi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061832197","display_name":"Jiasi Chen","orcid":"https://orcid.org/0000-0001-9923-9027"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Jiasi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070642269","display_name":"Sanja Fidler","orcid":"https://orcid.org/0000-0003-1040-3260"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fidler, Sanja","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137681936","display_name":"Huan Ling","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ling, Huan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5026841733","display_name":"Xuanchi Ren","orcid":"https://orcid.org/0000-0001-6376-7100"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ren, Xuanchi","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":0.34769999980926514,"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":0.34769999980926514,"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":0.3434000015258789,"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":0.013700000010430813,"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/component","display_name":"Component (thermodynamics)","score":0.5493000149726868},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5031999945640564},{"id":"https://openalex.org/keywords/rewriting","display_name":"Rewriting","score":0.49399998784065247},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4668999910354614},{"id":"https://openalex.org/keywords/enhancer","display_name":"Enhancer","score":0.4625000059604645},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/natural-language","display_name":"Natural language","score":0.4049000144004822}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7178000211715698},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.5493000149726868},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5031999945640564},{"id":"https://openalex.org/C154690210","wikidata":"https://www.wikidata.org/wiki/Q1668499","display_name":"Rewriting","level":2,"score":0.49399998784065247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49399998784065247},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4668999910354614},{"id":"https://openalex.org/C111936080","wikidata":"https://www.wikidata.org/wiki/Q913367","display_name":"Enhancer","level":4,"score":0.4625000059604645},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.45719999074935913},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.4049000144004822},{"id":"https://openalex.org/C2776674983","wikidata":"https://www.wikidata.org/wiki/Q545981","display_name":"Image editing","level":3,"score":0.3668999969959259},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34049999713897705},{"id":"https://openalex.org/C2779668609","wikidata":"https://www.wikidata.org/wiki/Q623092","display_name":"Rapid serial visual presentation","level":3,"score":0.33660000562667847},{"id":"https://openalex.org/C2780878386","wikidata":"https://www.wikidata.org/wiki/Q1659648","display_name":"Visual language","level":2,"score":0.33169999718666077},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.32190001010894775},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.30480000376701355},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3046000003814697},{"id":"https://openalex.org/C168820333","wikidata":"https://www.wikidata.org/wiki/Q448889","display_name":"Visual inspection","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2777055276","wikidata":"https://www.wikidata.org/wiki/Q7936580","display_name":"Visual approach","level":2,"score":0.2689000070095062},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2524999976158142},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.00204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00204","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.2606.00204","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.00204","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":{"Natural":[0],"language":[1,90],"has":[2],"become":[3],"a":[4,44,49,84,123],"powerful":[5],"interface":[6],"for":[7,126],"image":[8,159],"generation":[9,76,160],"and":[10,33,70,101,135,140,147,161],"editing,":[11],"yet":[12],"text-guided":[13],"visual":[14,36,75,145,154],"systems":[15],"remain":[16],"highly":[17],"sensitive":[18],"to":[19,73,178],"prompt":[20,41,111,148,168,180],"formulation.":[21],"Semantically":[22],"similar":[23],"requests":[24],"can":[25],"produce":[26],"different":[27],"outputs":[28],"depending":[29],"on":[30,58,157,188],"wording,":[31],"specificity,":[32],"how":[34],"explicitly":[35],"constraints":[37,129],"are":[38],"stated,":[39],"motivating":[40],"enhancement":[42,121],"as":[43,63,93],"trainable":[45],"component":[46],"rather":[47],"than":[48],"peripheral":[50],"user":[51],"choice.":[52],"Existing":[53],"strong":[54,187],"enhancers":[55,169],"often":[56],"rely":[57],"large,":[59],"proprietary":[60],"LLMs":[61],"such":[62],"ChatGPT":[64],"or":[65],"Gemini,":[66],"adding":[67],"cost,":[68],"latency,":[69],"deployment":[71],"dependence":[72],"the":[74,110,152,176],"pipeline.":[77],"We":[78],"propose":[79],"Agentic":[80],"Prompt":[81],"Enhancer":[82],"(APE),":[83],"lightweight":[85],"framework":[86],"that":[87,165],"post-trains":[88],"small":[89,167],"models":[91],"(SLMs)":[92],"prompt-enhancement":[94],"agents.":[95],"APE":[96,143],"supports":[97],"both":[98],"single-agent":[99,106],"rewriting":[100],"role-specialized":[102],"multi-agent":[103,117],"enhancement.":[104],"Its":[105],"instantiation,":[107,118],"SAPE,":[108],"rewrites":[109],"in":[112,182],"one":[113],"pass,":[114],"while":[115],"its":[116],"MAPE,":[119],"decomposes":[120],"into":[122],"router--rewriter--composer":[124],"process":[125],"handling":[127],"compositional":[128,190],"over":[130],"objects,":[131],"attributes,":[132],"spatial":[133],"relations,":[134],"edits.":[136],"With":[137],"task-aware":[138],"rewards":[139],"post-training":[141],"protocols,":[142],"improves":[144],"alignment":[146],"following":[149],"without":[150],"modifying":[151],"downstream":[153],"model.":[155],"Experiments":[156],"challenging":[158],"editing":[162],"benchmarks":[163],"demonstrate":[164],"post-trained":[166],"reliably":[170],"outperform":[171],"their":[172],"base":[173],"counterparts,":[174],"narrowing":[175],"gap":[177],"closed-source":[179],"enhancers;":[181],"addition,":[183],"MAPE":[184],"proves":[185],"particularly":[186],"complex":[189],"tasks":[191],"within":[192],"these":[193],"benchmarks.":[194]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}