{"id":"https://openalex.org/W7148869130","doi":"https://doi.org/10.48550/arxiv.2604.01985","title":"World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry","display_name":"World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry","publication_year":2026,"publication_date":"2026-04-02","ids":{"openalex":"https://openalex.org/W7148869130","doi":"https://doi.org/10.48550/arxiv.2604.01985"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.01985","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01985","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.2604.01985","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5132887689","display_name":"Yuejiang Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yuejiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132916521","display_name":"Fan Feng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng, Fan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102491705","display_name":"Lingjing Kong","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong, Lingjing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120793368","display_name":"Weifeng Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Weifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132838737","display_name":"Jinzhou Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Jinzhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132873862","display_name":"Kun Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Kun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132859805","display_name":"Kevin Murphy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Murphy, Kevin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132904269","display_name":"Chelsea Finn","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Finn, Chelsea","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5132839543","display_name":"Yilun Du","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Yilun","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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2842000126838684,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.2842000126838684,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.17219999432563782,"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":0.11980000138282776,"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/robustness","display_name":"Robustness (evolution)","score":0.6751999855041504},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.5447999835014343},{"id":"https://openalex.org/keywords/reachability","display_name":"Reachability","score":0.5364000201225281},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.5134000182151794},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5099999904632568},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44350001215934753},{"id":"https://openalex.org/keywords/possible-world","display_name":"Possible world","score":0.37209999561309814},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.35580000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7215999960899353},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6751999855041504},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.5447999835014343},{"id":"https://openalex.org/C136643341","wikidata":"https://www.wikidata.org/wiki/Q1361526","display_name":"Reachability","level":2,"score":0.5364000201225281},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5134000182151794},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5099999904632568},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4442000091075897},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44350001215934753},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4230000078678131},{"id":"https://openalex.org/C136172866","wikidata":"https://www.wikidata.org/wiki/Q1088088","display_name":"Possible world","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3395000100135803},{"id":"https://openalex.org/C3020493868","wikidata":"https://www.wikidata.org/wiki/Q55631277","display_name":"Real world data","level":2,"score":0.33709999918937683},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.3292999863624573},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.3086000084877014},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C110251889","wikidata":"https://www.wikidata.org/wiki/Q1569697","display_name":"Model checking","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.2752000093460083},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.25940001010894775},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.2556000053882599},{"id":"https://openalex.org/C135798126","wikidata":"https://www.wikidata.org/wiki/Q2167279","display_name":"Top-down and bottom-up design","level":2,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.01985","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01985","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.2604.01985","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.01985","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":[{"score":0.4465162456035614,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"General-purpose":[0],"world":[1,29,64,131],"models":[2,65],"promise":[3],"scalable":[4],"policy":[5,20,202],"evaluation,":[6],"optimization,":[7],"and":[8,72,90,118,143,167,190],"planning,":[9],"yet":[10],"achieving":[11],"the":[12,112,119],"required":[13],"level":[14],"of":[15,39,115,122,155],"robustness":[16],"remains":[17],"challenging.":[18],"Unlike":[19],"learning":[21],"which":[22,42],"primarily":[23],"focuses":[24],"on":[25],"optimal":[26],"actions,":[27,41,166],"a":[28,36,60,130,135,145,153],"model":[30,132,148],"needs":[31],"to":[32,66,78,108],"be":[33],"reliable":[34],"over":[35,205],"vast":[37],"space":[38],"suboptimal":[40],"are":[43],"often":[44,182],"underrepresented":[45],"in":[46,176],"action-labeled":[47],"robot":[48],"interactions.":[49],"To":[50],"address":[51],"this":[52],"challenge,":[53],"we":[54,128],"propose":[55],"World":[56],"Action":[57],"Verifier":[58],"(WAV),":[59],"framework":[61],"that":[62,95,149],"enables":[63],"identify":[67],"their":[68],"own":[69],"prediction":[70,82,106],"errors":[71],"self-improve.":[73],"The":[74],"key":[75],"idea":[76],"is":[77,99],"decompose":[79],"action-conditioned":[80],"state":[81,88,156],"into":[83],"two":[84,109],"independently":[85],"verifiable":[86],"factors:":[87],"plausibility":[89],"action":[91],"reachability.":[92],"We":[93],"show":[94],"verifying":[96],"these":[97,126],"factors":[98],"significantly":[100],"more":[101],"tractable":[102],"than":[103],"direct":[104],"forward":[105,168],"due":[107],"underlying":[110],"asymmetries:":[111],"broader":[113],"availability":[114],"action-free":[116],"data":[117],"lower":[120],"dimensionality":[121],"action-relevant":[123],"features.":[124,157],"Leveraging":[125],"asymmetries,":[127],"augment":[129],"with":[133],"(i)":[134],"diverse":[136],"subgoal":[137],"generator":[138],"obtained":[139],"from":[140,152],"video":[141],"corpora":[142],"(ii)":[144],"sparse":[146],"inverse":[147],"infers":[150],"actions":[151],"subset":[154],"By":[158],"enforcing":[159],"cycle":[160],"consistency":[161],"among":[162],"proposed":[163],"subgoals,":[164],"inferred":[165],"rollouts,":[169],"WAV":[170],"provides":[171],"an":[172],"effective":[173],"verification":[174],"mechanism":[175],"under-explored":[177],"regimes,":[178],"where":[179],"existing":[180],"methods":[181],"fail.":[183],"Across":[184],"nine":[185],"tasks":[186],"spanning":[187],"MiniGrid,":[188],"RoboMimic,":[189],"ManiSkill,":[191],"our":[192],"method":[193],"achieves":[194],"2x":[195],"higher":[196],"sample":[197],"efficiency":[198],"while":[199],"improving":[200],"downstream":[201],"performance":[203],"by":[204],"22%.":[206]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-04-04T00:00:00"}