{"id":"https://openalex.org/W7160827902","doi":"https://doi.org/10.48550/arxiv.2605.07630","title":"Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents","display_name":"Safe, or Simply Incapable? Rethinking Safety Evaluation for Phone-Use Agents","publication_year":2026,"publication_date":"2026-05-08","ids":{"openalex":"https://openalex.org/W7160827902","doi":"https://doi.org/10.48550/arxiv.2605.07630"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.07630","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07630","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.2605.07630","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5135881439","display_name":"Zhengyang Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Zhengyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135906144","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0002-1113-8465"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135866443","display_name":"Chenxin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Chenxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132743539","display_name":"Xin Lai","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lai, Xin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027156714","display_name":"Pengyuan Lyu","orcid":"https://orcid.org/0000-0003-3153-8519"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Pengyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101307330","display_name":"Yiduo Guo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Yiduo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135874236","display_name":"Weinong Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Weinong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135905725","display_name":"Junyi Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Junyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135892796","display_name":"Yang Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Yang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135879091","display_name":"Huawen Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Huawen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135855034","display_name":"Zhengyao Fang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fang, Zhengyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015989518","display_name":"Xingran Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Xingran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135852267","display_name":"Liang Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wu, Liang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135883559","display_name":"Fei Tang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tang, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113151725","display_name":"Sunqi Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Sunqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135282530","display_name":"Shangpin Peng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Shangpin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135832380","display_name":"Zheng Ruan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ruan, Zheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135838266","display_name":"Anran Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Anran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135834848","display_name":"Benyou Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Benyou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5132762025","display_name":"Chengquan Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Chengquan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5135836655","display_name":"Han Hu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Han","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/T10525","display_name":"Human-Automation Interaction and Safety","score":0.5095999836921692,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10525","display_name":"Human-Automation Interaction and Safety","score":0.5095999836921692,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12607","display_name":"Personal Information Management and User Behavior","score":0.05909999832510948,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.04280000180006027,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/safer","display_name":"SAFER","score":0.7348999977111816},{"id":"https://openalex.org/keywords/outcome","display_name":"Outcome (game theory)","score":0.6175000071525574},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5496000051498413},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5389999747276306},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.45339998602867126},{"id":"https://openalex.org/keywords/phone","display_name":"Phone","score":0.4277999997138977},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.39010000228881836}],"concepts":[{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.7348999977111816},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.6175000071525574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6101999878883362},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5389999747276306},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.49869999289512634},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.45339998602867126},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.43779999017715454},{"id":"https://openalex.org/C2778707766","wikidata":"https://www.wikidata.org/wiki/Q202064","display_name":"Phone","level":2,"score":0.4277999997138977},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.35600000619888306},{"id":"https://openalex.org/C153180980","wikidata":"https://www.wikidata.org/wiki/Q19776675","display_name":"Commit","level":2,"score":0.30720001459121704},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.2962999939918518},{"id":"https://openalex.org/C2780224610","wikidata":"https://www.wikidata.org/wiki/Q1530061","display_name":"Credibility","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C12174686","wikidata":"https://www.wikidata.org/wiki/Q1058438","display_name":"Risk assessment","level":2,"score":0.2531000077724457}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.07630","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07630","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.2605.07630","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.07630","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":[{"score":0.8117381930351257,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"When":[0],"a":[1,82,105,110,189,194,247],"phone-use":[2,134,148,260],"agent":[3,28],"avoids":[4],"harm,":[5],"does":[6,113,150],"that":[7,160,172],"show":[8],"safety,":[9],"or":[10,37,45,72,124],"simply":[11],"inability":[12,236,267],"to":[13,41,126,183,237,253,268],"act?":[14],"Existing":[15],"evaluations":[16],"often":[17,65],"cannot":[18],"tell.":[19],"A":[20],"harmful":[21,74],"outcome":[22,249],"may":[23],"be":[24],"avoided":[25],"because":[26,38],"the":[27,30,34,43,101,114,117,121,170,177,211,228],"recognized":[29],"risk":[31],"and":[32,57,108,203,207,235,242],"chose":[33],"safe":[35,118],"action,":[36,119,123],"it":[39],"failed":[40],"understand":[42],"screen":[44],"execute":[46],"any":[47],"relevant":[48],"action":[49,179],"at":[50,104,156],"all.":[51],"These":[52],"cases":[53],"have":[54],"different":[55,60],"causes":[56],"call":[58],"for":[59],"fixes,":[61],"yet":[62],"current":[63],"benchmarks":[64],"merge":[66],"them":[67],"under":[68,136],"task":[69],"success,":[70],"refusal,":[71],"final":[73],"outcome.":[75],"We":[76,130],"address":[77],"this":[78,137],"problem":[79],"with":[80],"PhoneSafety,":[81],"benchmark":[83],"of":[84,257],"700":[85],"safety-critical":[86],"moments":[87],"drawn":[88],"from":[89,266],"real":[90],"phone":[91],"interactions":[92],"across":[93],"more":[94,174,201,240],"than":[95,193],"130":[96],"apps.":[97],"Each":[98],"instance":[99],"isolates":[100],"next":[102,178],"decision":[103],"risky":[106,157],"moment":[107],"asks":[109],"simple":[111],"question:":[112],"model":[115,229],"take":[116,120],"unsafe":[122,223,264],"fail":[125],"do":[127,184],"anything":[128,185],"useful?":[129],"evaluate":[131],"eight":[132],"representative":[133],"agents":[135,261],"framework.":[138],"Our":[139],"results":[140],"reveal":[141],"two":[142,220],"main":[143],"patterns.":[144],"First,":[145],"stronger":[146],"general":[147],"ability":[149],"not":[151,168,251],"reliably":[152],"imply":[153],"safer":[154],"choices":[155,224],"moments.":[158],"Models":[159],"perform":[161],"better":[162],"on":[163],"ordinary":[164],"app":[165],"tasks":[166],"are":[167,198],"always":[169],"ones":[171],"behave":[173,187],"safely":[175],"when":[176,210],"matters.":[180],"Second,":[181],"failures":[182,217],"useful":[186],"like":[188],"capability":[190],"signal":[191],"rather":[192],"safety":[195],"signal:":[196],"they":[197],"concentrated":[199],"in":[200,225,239],"visually":[202,241],"operationally":[204,243],"demanding":[205,244],"settings":[206,226],"remain":[208],"stable":[209],"evaluation":[212],"protocol":[213],"changes.":[214],"Across":[215],"models,":[216],"split":[218],"into":[219],"recurring":[221],"patterns:":[222],"where":[227],"can":[230],"act":[231,238],"but":[232],"chooses":[233],"wrongly,":[234],"screens.":[245],"Overall,":[246],"harmless":[248],"is":[250],"enough":[252],"count":[254],"as":[255],"evidence":[256],"safety.":[258],"Evaluating":[259],"requires":[262],"separating":[263],"judgment":[265],"act.":[269]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-12T00:00:00"}
