{"id":"https://openalex.org/W7204165090","doi":"https://doi.org/10.48550/arxiv.2608.22421","title":"Where World Models Break: Natural-Input Failure Discovery","display_name":"Where World Models Break: Natural-Input Failure Discovery","publication_year":2026,"publication_date":"2026-08-23","ids":{"openalex":"https://openalex.org/W7204165090","doi":"https://doi.org/10.48550/arxiv.2608.22421"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.22421","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22421","pdf_url":"https://arxiv.org/pdf/2608.22421","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2608.22421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5130668752","display_name":"Zhanpeng Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I99418890","display_name":"San Francisco Bay University","ror":"https://ror.org/05wn69s11","country_code":"US","type":"education","lineage":["https://openalex.org/I99418890"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Shi, Zhanpeng","raw_affiliation_strings":["Equal contribution","School of Computer Science , Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution","institution_ids":[]},{"raw_affiliation_string":"School of Computer Science , Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004","https://openalex.org/I99418890"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148069912","display_name":"Zi Liang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Liang, Zi","raw_affiliation_strings":["Equal contribution","The Hong Kong Polytechnic University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Equal contribution","institution_ids":[]},{"raw_affiliation_string":"The Hong Kong Polytechnic University","institution_ids":["https://openalex.org/I14243506"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125031925","display_name":"Rong Feng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Feng, Rong","raw_affiliation_strings":["Department of Data Science , City University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science , City University of Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146547578","display_name":"Shiqin Tang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Shiqin","raw_affiliation_strings":["Centre for Artificial Intelligence and Robotics , Hong Kong Institute of Science & Innovation ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Centre for Artificial Intelligence and Robotics , Hong Kong Institute of Science & Innovation ,","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5146542728","display_name":"Xuyang Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN","SG"],"is_corresponding":false,"raw_author_name":"Chen, Xuyang","raw_affiliation_strings":["Chinese Academy of Sciences","Department of Electrical and Computer Engineering , National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chinese Academy of Sciences","institution_ids":["https://openalex.org/I19820366"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering , National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081924890","display_name":"Hongzong Li","orcid":"https://orcid.org/0000-0002-5774-7557","observed_orcids":["https://orcid.org/0000-0002-5774-7557","https://orcid.org/0009-0007-7857-1689"]},"institutions":[{"id":"https://openalex.org/I17145004","display_name":"Northwestern Polytechnical University","ror":"https://ror.org/01y0j0j86","country_code":"CN","type":"education","lineage":["https://openalex.org/I17145004"]},{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I99418890","display_name":"San Francisco Bay University","ror":"https://ror.org/05wn69s11","country_code":"US","type":"education","lineage":["https://openalex.org/I99418890"]}],"countries":["CN","HK","US"],"is_corresponding":false,"raw_author_name":"Li, Hongzong","raw_affiliation_strings":["Generative AI Research and Development Center , The Hong Kong University of Science and Technology","School of Computer Science , Northwestern Polytechnical University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Generative AI Research and Development Center , The Hong Kong University of Science and Technology","institution_ids":["https://openalex.org/I200769079"]},{"raw_affiliation_string":"School of Computer Science , Northwestern Polytechnical University","institution_ids":["https://openalex.org/I17145004","https://openalex.org/I99418890"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9042999744415283,"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":0.9042999744415283,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.04809999838471413,"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.01679999940097332,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/world-models","display_name":"world models","score":0.9909999966621399}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7009000182151794},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.671500027179718},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.5523999929428101},{"id":"https://openalex.org/C112987892","wikidata":"https://www.wikidata.org/wiki/Q5051574","display_name":"Catastrophic failure","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.31119999289512634},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.3073999881744385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30230000615119934},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2971999943256378},{"id":"https://openalex.org/C141603448","wikidata":"https://www.wikidata.org/wiki/Q134830","display_name":"Prefix","level":2,"score":0.29170000553131104},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2912999987602234},{"id":"https://openalex.org/C119323957","wikidata":"https://www.wikidata.org/wiki/Q5048226","display_name":"Cascading failure","level":4,"score":0.28870001435279846},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2705000042915344},{"id":"https://openalex.org/C2777317252","wikidata":"https://www.wikidata.org/wiki/Q18393516","display_name":"Rare events","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C106306483","wikidata":"https://www.wikidata.org/wiki/Q183984","display_name":"Futures contract","level":2,"score":0.26589998602867126},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26019999384880066}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.22421","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22421","pdf_url":"https://arxiv.org/pdf/2608.22421","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.22421","doi":"https://doi.org/10.48550/arxiv.2608.22421","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.22421","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.22421","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.22421","pdf_url":"https://arxiv.org/pdf/2608.22421","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-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204165090.pdf","grobid_xml":"https://content.openalex.org/works/W7204165090.grobid-xml"},"referenced_works_count":6,"referenced_works":["https://openalex.org/W7126247852","https://openalex.org/W7131224282","https://openalex.org/W7140141371","https://openalex.org/W7156160916","https://openalex.org/W7160245766","https://openalex.org/W7162283551"],"related_works":["https://openalex.org/W7221530852","https://openalex.org/W7221048195","https://openalex.org/W7166128717","https://openalex.org/W7125501301","https://openalex.org/W7215023951","https://openalex.org/W7162777228","https://openalex.org/W7220461499","https://openalex.org/W7215887867","https://openalex.org/W7213260655","https://openalex.org/W7223248154"],"abstract_inverted_index":{"World":[0],"models":[1,22],"predict":[2],"action-conditioned":[3],"futures":[4],"and":[5,14,36,100,116,172,187,193],"serve":[6],"as":[7,30,131],"critical":[8,126],"internal":[9],"simulators":[10],"for":[11],"downstream":[12],"planning":[13],"control.":[15,214],"However,":[16],"catastrophic":[17,73],"prediction":[18,106],"failures":[19,111,127],"of":[20,148,162],"world":[21,48],"could":[23],"dangerously":[24],"propagate":[25],"through":[26],"the":[27,41,70,87,145,159],"control":[28],"pipeline,":[29],"subsequent":[31],"agent":[32],"or":[33,77,140],"model":[34,71],"training":[35],"decision-making":[37],"depend":[38],"heavily":[39],"on":[40,113],"continuous":[42],"environment":[43],"evolution":[44],"forecasted":[45],"by":[46,56,175],"these":[47,110],"models.":[49],"Existing":[50],"evaluations":[51,200],"overlook":[52],"this":[53,83],"systemic":[54],"risk:":[55],"aggregating":[57],"average":[58],"errors":[59],"over":[60],"benign":[61],"generations":[62],"from":[63],"general":[64],"queries,":[65],"they":[66],"fail":[67,201],"to":[68,202],"stress-test":[69],"against":[72],"collapses":[74],"under":[75,92,120],"rare":[76],"unobserved":[78],"condition-action":[79,133],"combinations.":[80],"To":[81,151],"bridge":[82],"gap,":[84],"we":[85,154],"formalize":[86],"natural-input":[88],"failure":[89,196],"discovery":[90],"problem:":[91],"a":[93],"finite":[94],"query":[95],"budget,":[96],"finding":[97],"environment-valid":[98],"conditions":[99],"action":[101],"prefixes":[102],"that":[103,198,205],"induce":[104],"severe":[105],"risk,":[107],"verifying":[108],"whether":[109],"reproduce":[112],"fresh":[114],"seeds,":[115],"testing":[117],"their":[118],"persistence":[119],"nearby":[121],"valid":[122,132,163],"edits.":[123],"Discovering":[124],"such":[125],"is":[128],"computationally":[129],"challenging,":[130],"combinations":[134],"explode":[135],"exponentially,":[136],"rendering":[137],"exhaustive":[138],"search":[139,179],"standard":[141],"sampling":[142],"infeasible":[143],"given":[144],"high":[146],"cost":[147],"noisy":[149],"rollouts.":[150],"tackle":[152],"this,":[153],"propose":[155],"BasinLens,":[156],"which":[157],"exploits":[158],"underlying":[160],"structure":[161],"inputs,":[164],"where":[165],"each":[166],"coordinate":[167],"possesses":[168],"environment-defined":[169],"semantic":[170],"types":[171],"admissible":[173],"domains,":[174],"pairing":[176],"uncertainty-guided":[177],"global":[178],"with":[180],"typed":[181],"local":[182],"replacements.":[183],"Across":[184],"diverse":[185],"benchmarks":[186,207],"world-model":[188],"families,":[189],"BasinLens":[190],"exposes":[191],"reproducible":[192],"locally":[194],"persistent":[195],"modes":[197],"conventional":[199],"reveal,":[203],"showing":[204],"average-case":[206],"can":[208],"mask":[209],"important":[210],"vulnerabilities":[211],"in":[212],"world-model-driven":[213]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}