{"id":"https://openalex.org/W7224877434","doi":"https://doi.org/10.48550/arxiv.2610.39158","title":"VEvo-Harness: Causally-Guarded Self-Evolving Harness for Agentic Image Generation","display_name":"VEvo-Harness: Causally-Guarded Self-Evolving Harness for Agentic Image Generation","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224877434","doi":"https://doi.org/10.48550/arxiv.2610.39158"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39158","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39158","pdf_url":"https://arxiv.org/pdf/2610.39158","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":"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/2610.39158","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160236817","display_name":"Yuan Wang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Yuan","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160205143","display_name":"Yuhang Yu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu, Yuhang","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160217107","display_name":"Mengting Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Mengting","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038594920","display_name":"Tianrun Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu, Tianrun","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160160425","display_name":"Zihao Pan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Pan, Zihao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055185546","display_name":"Xuetao Feng","orcid":"https://orcid.org/0000-0002-1309-8954","observed_orcids":["https://orcid.org/0000-0002-1309-8954"]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng, Xuetao","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5160172679","display_name":"Wei Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Wei","raw_affiliation_strings":["Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"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":0.9951000213623047,"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":0.9951000213623047,"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":0.0031999999191612005,"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/T14254","display_name":"Digital Media and Visual Art","score":0.00019999999494757503,"subfield":{"id":"https://openalex.org/subfields/1704","display_name":"Computer Graphics and Computer-Aided Design"},"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/visual-generation","display_name":"visual generation","score":0.33899998664855957},{"id":"https://openalex.org/keywords/visual-editing","display_name":"visual editing","score":0.6499999761581421},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7009999752044678},{"id":"https://openalex.org/keywords/hierarchical-verification","display_name":"hierarchical verification","score":0.7289999723434448},{"id":"https://openalex.org/keywords/skill-library","display_name":"skill library","score":0.8259999752044678},{"id":"https://openalex.org/keywords/counterfactual-image-generation","display_name":"counterfactual image generation","score":0.6399999856948853}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6514000296592712},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6328999996185303},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4620000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.453900009393692},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.41920000314712524},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.40560001134872437},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.39969998598098755},{"id":"https://openalex.org/C84945661","wikidata":"https://www.wikidata.org/wiki/Q7366567","display_name":"Root cause","level":2,"score":0.37929999828338623},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.3709000051021576},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.3140999972820282},{"id":"https://openalex.org/C74172769","wikidata":"https://www.wikidata.org/wiki/Q1446839","display_name":"Routing (electronic design automation)","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2944999933242798},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.29249998927116394},{"id":"https://openalex.org/C2776633867","wikidata":"https://www.wikidata.org/wiki/Q186612","display_name":"Timer","level":3,"score":0.2597000002861023},{"id":"https://openalex.org/C171078966","wikidata":"https://www.wikidata.org/wiki/Q111029","display_name":"Root (linguistics)","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C111370547","wikidata":"https://www.wikidata.org/wiki/Q7451120","display_name":"Sensory cue","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39158","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39158","pdf_url":"https://arxiv.org/pdf/2610.39158","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2610.39158","doi":"https://doi.org/10.48550/arxiv.2610.39158","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39158","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":"cc-by-nc-sa","license_id":"https://openalex.org/licenses/cc-by-nc-sa","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2610.39158","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39158","pdf_url":"https://arxiv.org/pdf/2610.39158","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224877434.pdf","grobid_xml":"https://content.openalex.org/works/W7224877434.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7212004655","https://openalex.org/W7213431113","https://openalex.org/W7207819196","https://openalex.org/W7212161483","https://openalex.org/W7162101076","https://openalex.org/W7221963828","https://openalex.org/W7167233610","https://openalex.org/W7221809895","https://openalex.org/W7162774592","https://openalex.org/W7159669308"],"abstract_inverted_index":{"The":[0],"central":[1],"bottleneck":[2],"in":[3],"visual":[4,37,86,95,111],"generation":[5,26,125],"and":[6,53,140,150,187,200],"editing":[7],"has":[8],"migrated":[9],"from":[10],"achieving":[11],"pixel-level":[12],"fidelity":[13],"to":[14,176],"satisfying":[15],"densely":[16],"constrained":[17],"user":[18],"specifications":[19],"through":[20,121],"increasingly":[21],"agentic":[22,25,85,185],"workflows.":[23],"Prevailing":[24],"pipelines":[27],"remain":[28],"shallow":[29],"generate-verify-rewrite":[30],"loops":[31],"treating":[32],"VLM":[33],"judgments":[34,100],"as":[35],"coarse":[36],"feedback,":[38],"either":[39],"discarding":[40],"repair":[41,166],"experience":[42],"or":[43],"admitting":[44],"ungated":[45],"updates":[46],"that":[47,97,114,132,159],"poison":[48],"skill":[49,119,146],"library.":[50],"With":[51],"memorize":[52],"govern":[54],"periods":[55],"left":[56],"open,":[57],"they":[58],"degrade":[59],"into":[60,101,143],"ungoverned":[61],"iterators":[62],"of":[63,148,165],"repeated":[64],"trial-and-error":[65],"rather":[66],"than":[67],"continual":[68,80,112,197],"self-evolving":[69,81],"harness.":[70],"Towards":[71],"this":[72],"issue,":[73],"we":[74],"present":[75],"\\textbf{VEvo-Harness},":[76],"the":[77,178,196],"first":[78],"causally-guarded":[79],"harness":[82,130,198],"system":[83],"for":[84],"generation.":[87],"VEvo-Harness":[88,182],"introduces":[89],"four":[90],"coupled":[91],"innovations:":[92],"(1)":[93],"\\textit{a":[94,110,128,155],"traceback}":[96],"densifies":[98],"sparse":[99],"root-cause":[102],"attributions":[103],"with":[104],"a":[105,144,161],"hierarchical":[106],"verification":[107],"tree;":[108],"(2)":[109],"governance}":[113],"admits":[115],"only":[116],"causally":[117,151],"valid":[118],"patches":[120],"counterfactual":[122],"dual-arm":[123],"image":[124],"replay;":[126],"(3)":[127],"lifecycle-managed":[129],"state}":[131],"hierarchically":[133],"distills":[134],"root-cause-anchored":[135],"episodes":[136],"across":[137],"working,":[138],"experience,":[139],"pattern":[141],"tiers":[142],"persistent":[145],"library":[147],"routable":[149],"verified":[152],"capabilities;":[153],"(4)":[154],"heterogeneous":[156],"sandbox":[157],"policy}":[158],"orchestrates":[160],"diverse":[162],"action":[163],"space":[164],"primitives,":[167],"dynamically":[168],"routing":[169],"cost-aware":[170],"interventions":[171],"based":[172],"on":[173],"root":[174],"causes":[175],"select":[177],"most":[179],"effective":[180],"strategy.":[181],"surpasses":[183],"state-of-the-art":[184],"methods":[186],"rivals":[188],"proprietary":[189],"generators":[190],"(\\textit{e.g.},":[191],"GPT-Image,":[192],"Nano-Pro)":[193],"while":[194],"maintaining":[195],"evolution":[199],"generalization.":[201]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-31T00:00:00"}