{"id":"https://openalex.org/W7162101076","doi":"https://doi.org/10.48550/arxiv.2605.21605","title":"GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation","display_name":"GenEvolve: Self-Evolving Image Generation Agents via Tool-Orchestrated Visual Experience Distillation","publication_year":2026,"publication_date":"2026-05-20","ids":{"openalex":"https://openalex.org/W7162101076","doi":"https://doi.org/10.48550/arxiv.2605.21605"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.21605","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21605","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.2605.21605","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136742552","display_name":"Sixiang Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Sixiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136735559","display_name":"Zhaohu Xing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xing, Zhaohu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136749669","display_name":"Tian Ye","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye, Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136813037","display_name":"Xinyu Geng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Geng, Xinyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136767858","display_name":"Yunlong Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin, Yunlong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136753831","display_name":"Jianyu Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Jianyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136770881","display_name":"Xuanhua He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Xuanhua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064248881","display_name":"Fuxiang Zhai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhai, Fuxiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136788938","display_name":"Jialin Gao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gao, Jialin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136795263","display_name":"Zhu, Lei, 1980-","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhu, Lei","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":0.48559999465942383,"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":0.48559999465942383,"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":0.3716000020503998,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.013000000268220901,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/generative-grammar","display_name":"Generative grammar","score":0.6365000009536743},{"id":"https://openalex.org/keywords/construct","display_name":"Construct (python library)","score":0.5716000199317932},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.44530001282691956},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.4138000011444092},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.412200003862381}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7229999899864197},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.6365000009536743},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.5716000199317932},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5430999994277954},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.44530001282691956},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.4138000011444092},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4077000021934509},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3465999960899353},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3465000092983246},{"id":"https://openalex.org/C2987933465","wikidata":"https://www.wikidata.org/wiki/Q141130","display_name":"Image manipulation","level":3,"score":0.30399999022483826},{"id":"https://openalex.org/C2992829110","wikidata":"https://www.wikidata.org/wiki/Q3921615","display_name":"First generation","level":3,"score":0.2662999927997589}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.21605","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21605","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.2605.21605","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.21605","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7584308981895447}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-ended":[0],"image":[1],"generation":[2,11,53,73,89,101],"is":[3,75,184],"no":[4],"longer":[5],"a":[6,18,37,61,78,95,129],"simple":[7],"prompt-to-image":[8],"problem.":[9],"High-quality":[10],"often":[12],"requires":[13],"an":[14],"agent":[15,40,83],"to":[16,35,128],"combine":[17],"model's":[19],"internal":[20],"generative":[21],"ability":[22],"with":[23],"external":[24],"resources.":[25],"As":[26],"requests":[27],"become":[28],"more":[29,49],"diverse":[30],"and":[31,46,91,118,154,161,167],"demanding,":[32],"we":[33,58],"aim":[34],"develop":[36],"general":[38],"image-generation":[39,180],"that":[41,103],"can":[42],"self-evolve":[43],"through":[44],"trajectories":[45,113],"use":[47],"tools":[48],"effectively":[50],"across":[51],"varied":[52],"challenges.":[54],"To":[55],"this":[56],"end,":[57],"propose":[59],"GenEvolve,":[60,71],"self-evolving":[62],"framework":[63],"based":[64],"on":[65,106,164],"Tool-Orchestrated":[66],"Visual":[67,137],"Experience":[68,138],"Distillation.":[69],"In":[70],"each":[72],"attempt":[74],"modeled":[76],"as":[77,185],"tool-orchestrated":[79],"trajectory,":[80],"where":[81],"the":[82,115,145],"gathers":[84],"evidence,":[85],"selects":[86],"references,":[87],"invokes":[88],"skills,":[90],"composes":[92],"them":[93],"into":[94,122],"prompt-reference":[96],"program.":[97],"Unlike":[98],"existing":[99],"agentic":[100],"methods":[102],"mainly":[104],"rely":[105],"image-level":[107],"scalar":[108],"rewards,":[109],"GenEvolve":[110],"compares":[111],"multiple":[112],"for":[114],"same":[116],"request":[117],"abstracts":[119],"best-worst":[120],"differences":[121],"structured":[123],"visual":[124],"experience,":[125],"provided":[126],"only":[127],"privileged":[130],"teacher":[131],"branch.":[132],"Inspired":[133],"by":[134],"on-policy":[135],"self-distillation,":[136],"Distillation":[139],"provides":[140],"dense":[141],"token-level":[142],"supervision,":[143],"helping":[144],"student":[146],"internalize":[147],"better":[148],"search,":[149],"knowledge":[150],"activation,":[151],"reference":[152],"selection,":[153],"prompt":[155],"construction.":[156],"We":[157],"further":[158],"construct":[159],"GenEvolve-Data":[160],"GenEvolve-Bench.":[162],"Experiments":[163],"public":[165],"benchmarks":[166],"GenEvolve-Bench":[168],"show":[169],"substantial":[170],"gains":[171],"over":[172],"strong":[173],"baselines,":[174],"achieving":[175],"state-of-the-art":[176],"performance":[177],"among":[178],"current":[179],"frameworks.":[181],"Our":[182],"website":[183],"follows:":[186],"https://ephemeral182.github.io/GenEvolve/":[187]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-23T00:00:00"}