{"id":"https://openalex.org/W7161819624","doi":"https://doi.org/10.48550/arxiv.2605.19639","title":"Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation","display_name":"Benchmarking and Evolving Reason-Reflect-Rectify for Reflective Visual Generation","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7161819624","doi":"https://doi.org/10.48550/arxiv.2605.19639"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.19639","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19639","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.2605.19639","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136584732","display_name":"Junjie Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Junjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038369604","display_name":"Xinghua Lou","orcid":"https://orcid.org/0009-0005-2384-2897"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lou, Xinghua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136539915","display_name":"Jason Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jason","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136582097","display_name":"Ye Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Ye","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136542635","display_name":"Keyu Chen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Keyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136564544","display_name":"Yulin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yulin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023868028","display_name":"Bin Kang","orcid":"https://orcid.org/0000-0002-6054-7556"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kang, Bin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136591099","display_name":"Jacky Mai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mai, Jacky","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136592071","display_name":"Yanwei Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Yanwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136580788","display_name":"Zhuotao Tian","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tian, Zhuotao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136520865","display_name":"Liqiang Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Liqiang","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":0.5666000247001648,"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":0.5666000247001648,"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":0.21389999985694885,"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/T10799","display_name":"Data Visualization and Analytics","score":0.018699999898672104,"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/rectification","display_name":"Rectification","score":0.7811999917030334},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7458999752998352},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6284999847412109},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.43810001015663147},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4088999927043915},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.40880000591278076},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4016999900341034},{"id":"https://openalex.org/keywords/iterative-and-incremental-development","display_name":"Iterative and incremental development","score":0.3831000030040741},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.35269999504089355}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860999703407288},{"id":"https://openalex.org/C50942859","wikidata":"https://www.wikidata.org/wiki/Q4967193","display_name":"Rectification","level":3,"score":0.7811999917030334},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7458999752998352},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6284999847412109},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5167999863624573},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.43810001015663147},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4088999927043915},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.40880000591278076},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.3831000030040741},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.35269999504089355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34380000829696655},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.3384999930858612},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3149999976158142},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2851000130176544},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.2678999900817871},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.2662999927997589},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.26600000262260437},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.2621000111103058},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.2615000009536743},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2563999891281128},{"id":"https://openalex.org/C3018907156","wikidata":"https://www.wikidata.org/wiki/Q7785058","display_name":"Third generation","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.25279998779296875}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.19639","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19639","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.2605.19639","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.19639","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":{"Text-to-Image":[0],"(T2I)":[1],"models":[2,76,151],"and":[3,50,64,104,135,154],"Unified":[4],"Multimodal":[5],"Models":[6],"(UMMs)":[7],"have":[8],"achieved":[9],"remarkable":[10],"progress":[11],"in":[12,127,132],"visual":[13],"generation.":[14],"However,":[15],"their":[16,24],"reliance":[17],"on":[18,68,124,152],"a":[19,47,53,71,95,105],"single-pass":[20],"generation":[21,79,146],"paradigm":[22],"limits":[23],"ability":[25],"to":[26,83,110,143],"handle":[27],"complex":[28],"prompts":[29],"requiring":[30],"iterative":[31,62],"refinement.":[32],"To":[33,88],"enable":[34],"multi-round":[35],"Reflective":[36,128],"Visual":[37],"Generation":[38],"(RVG),":[39],"we":[40,92],"formalize":[41],"the":[42,145],"Reason-Reflect-Rectify":[43],"(R^3)":[44],"loop":[45],"as":[46],"core":[48],"framework":[49,97],"introduce":[51],"R^3-Bench,":[52],"benchmark":[54],"of":[55,148],"over":[56],"600":[57],"expert-annotated":[58],"instances":[59],"that":[60,119],"quantifies":[61],"reasoning":[63],"rectification":[65,86,113],"capabilities.":[66],"Evaluation":[67],"R^3-Bench":[69,125],"reveals":[70],"critical":[72],"gap:":[73],"while":[74],"state-of-the-art":[75],"can":[77,136],"identify":[78],"errors,":[80],"they":[81],"fail":[82],"generate":[84],"actionable":[85],"instructions.":[87],"bridge":[89],"this":[90],"gap,":[91],"propose":[93],"R^3-Refiner,":[94],"dual-stage":[96],"leveraging":[98],"Group":[99],"Relative":[100],"Policy":[101],"Optimization":[102],"(GRPO)":[103],"Hierarchical":[106],"Reward":[107],"Mechanism":[108],"(HRM)":[109],"better":[111],"align":[112],"with":[114,140],"reflective":[115],"reasoning.":[116],"Experiments":[117],"show":[118],"R^3-Refiner":[120],"achieves":[121],"significant":[122],"improvements":[123],"(+12.0%":[126],"Verdict":[129],"Score,":[130],"+9.0%":[131],"Rectification":[133],"Score),":[134],"be":[137],"seamlessly":[138],"integrated":[139],"various":[141],"MLLMs":[142],"enhance":[144],"quality":[147],"different":[149],"T2I":[150],"GenEval++":[153],"T2I-CompBench.":[155],"Code":[156],"is":[157],"available":[158],"at":[159],"https://github.com/xiaomoguhz/R3-Bench.":[160]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-21T00:00:00"}