{"id":"https://openalex.org/W7204245205","doi":"https://doi.org/10.18653/2026.emnlp-main.266","title":"Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments","display_name":"Are Android GUI Agents Robust Against Runtime Anomalies? AnTrap: Evaluating Agents in Dynamic Adversarial Environments","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7204245205","doi":"https://doi.org/10.18653/2026.emnlp-main.266"},"language":"en","primary_location":{"id":"doi:10.18653/2026.emnlp-main.266","doi":"https://doi.org/10.18653/2026.emnlp-main.266","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.266","pdf_url":"https://aclanthology.org/2026.emnlp-main.266.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.emnlp-main.266.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007485947","display_name":"Guo Gan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Guo Gan","raw_affiliation_strings":["Zhejiang University Y Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University Y Yale University","institution_ids":["https://openalex.org/I32971472","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125538427","display_name":"Yilun Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I32971472","display_name":"Yale University","ror":"https://ror.org/03v76x132","country_code":"US","type":"education","lineage":["https://openalex.org/I32971472"]},{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Yilun Zhao","raw_affiliation_strings":["Zhejiang University Y Yale University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Zhejiang University Y Yale University","institution_ids":["https://openalex.org/I32971472","https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133297382","display_name":"Cong Chen","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cong Chen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125489091","display_name":"Jinbiao Wei","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jinbiao Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123657836","display_name":"Tingyu Song","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tingyu Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148385642","display_name":"Zheyuan Yang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheyuan Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137976520","display_name":"Lin Fu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lin Fu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5148310494","display_name":"Hong Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Zhou","raw_affiliation_strings":["T Tongji University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"T Tongji University","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.68050638,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6046","last_page":"6069"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.7261000275611877,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.7261000275611877,"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":0.1316000074148178,"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"}},{"id":"https://openalex.org/T13287","display_name":"Robotic Process Automation Applications","score":0.015200000256299973,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/gui-agents","display_name":"GUI agents","score":0.7559999823570251},{"id":"https://openalex.org/keywords/android","display_name":"Android","score":0.5329999923706055},{"id":"https://openalex.org/keywords/robustness-analysis","display_name":"robustness analysis","score":0.6690000295639038},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.41600000858306885},{"id":"https://openalex.org/keywords/adversarial-perturbations","display_name":"adversarial perturbations","score":0.7360000014305115},{"id":"https://openalex.org/keywords/adversarial-reinforcement-learning","display_name":"adversarial reinforcement learning","score":0.722000002861023},{"id":"https://openalex.org/keywords/group-relative-policy-optimization","display_name":"Group Relative Policy Optimization","score":0.6290000081062317},{"id":"https://openalex.org/keywords/agent-evaluation","display_name":"agent evaluation","score":0.3160000145435333}],"concepts":[{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.8773999810218811},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7752000093460083},{"id":"https://openalex.org/C557433098","wikidata":"https://www.wikidata.org/wiki/Q94","display_name":"Android (operating system)","level":2,"score":0.5256999731063843},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5224000215530396},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.48030000925064087},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3856000006198883},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36399999260902405},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3605000078678131},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3555000126361847},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.335999995470047},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C181335050","wikidata":"https://www.wikidata.org/wiki/Q14915018","display_name":"Swarm behaviour","level":2,"score":0.2976999878883362},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.2840000092983246},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C58642233","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Taxonomy (biology)","level":2,"score":0.27459999918937683}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/2026.emnlp-main.266","doi":"https://doi.org/10.18653/2026.emnlp-main.266","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.266","pdf_url":"https://aclanthology.org/2026.emnlp-main.266.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2608.24099","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24099","pdf_url":"https://arxiv.org/pdf/2608.24099","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.2608.24099","doi":"https://doi.org/10.48550/arxiv.2608.24099","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24099","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":"doi:10.18653/2026.emnlp-main.266","doi":"https://doi.org/10.18653/2026.emnlp-main.266","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.emnlp-main.266","pdf_url":"https://aclanthology.org/2026.emnlp-main.266.pdf","source":{"id":"https://openalex.org/S4363608991","display_name":"Conference on Empirical Methods in Natural Language Processing (EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G5949402452","display_name":null,"funder_award_id":"2025C02104","funder_id":"https://openalex.org/F4320338469","funder_display_name":"Science and Technology Program of Zhejiang Province"}],"funders":[{"id":"https://openalex.org/F4320338469","display_name":"Science and Technology Program of Zhejiang Province","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204245205.pdf","grobid_xml":"https://content.openalex.org/works/W7204245205.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4416550652","https://openalex.org/W7202170084","https://openalex.org/W4415346178","https://openalex.org/W4398836283","https://openalex.org/W7220987260","https://openalex.org/W7222200977","https://openalex.org/W4415311891","https://openalex.org/W7215048501","https://openalex.org/W4414726870","https://openalex.org/W7125166579"],"abstract_inverted_index":{"GUI":[0,76],"agents":[1],"often":[2],"encounter":[3],"dynamic":[4,36,83],"anomalies":[5,47,110],"when":[6],"deployed":[7],"on":[8],"Android":[9],"devices,":[10],"from":[11,111],"unexpected":[12],"pop-ups":[13],"to":[14,82,104],"action":[15,123],"misuse,":[16],"yet":[17],"existing":[18],"benchmarks":[19],"lack":[20],"systematic":[21],"evaluation":[22],"of":[23],"agent":[24,39],"robustness":[25],"against":[26],"runtime":[27],"anomalies.We":[28],"introduce":[29],"ANTRAP,":[30],"a":[31,43,62],"comprehensive":[32],"benchmark":[33],"that":[34,65,116,141],"injects":[35],"perturbations":[37],"into":[38,48],"execution":[40],"trajectories.We":[41],"propose":[42],"taxonomy":[44],"organizing":[45],"real-world":[46],"four":[49],"layers":[50,124],"(State,":[51],"Thinking,":[52],"Action":[53],"and":[54,60,101,122],"Round)":[55],"with":[56,85,149],"ten":[57],"fine-grained":[58],"subcategories,":[59],"develop":[61],"construction":[63],"pipeline":[64],"preserves":[66],"task":[67],"solvability":[68],"while":[69,117],"introducing":[70],"realistic":[71],"adversarial":[72,102,129],"conditions.Evaluating":[73],"16":[74],"leading":[75],"models,":[77],"we":[78,94],"reveal":[79],"universal":[80],"vulnerability":[81],"anomalies,":[84],"even":[86],"the":[87],"strongest":[88],"models":[89],"suffering":[90],"significant":[91],"performance":[92],"degradation.Furthermore,":[93],"conduct":[95],"GRPO":[96],"training":[97,146],"in":[98,147],"both":[99],"original":[100],"environments":[103,148],"validate":[105],"our":[106],"benchmark,":[107],"separating":[108],"environment-learnable":[109],"reasoning-bottlenecked":[112],"ones.Our":[113],"findings":[114],"show":[115],"single-step":[118],"traps":[119,150],"at":[120],"state":[121,136],"are":[125],"largely":[126],"addressable":[127],"through":[128],"reinforcement":[130],"learning,":[131],"deep":[132],"contextual":[133],"traps,":[134],"like":[135],"deadlock,":[137],"expose":[138],"intrinsic":[139],"limitations":[140],"cannot":[142],"be":[143],"resolved":[144],"by":[145],"alone.":[151]},"counts_by_year":[],"updated_date":"2026-11-01T11:40:01.658920","created_date":"2026-08-27T00:00:00"}