{"id":"https://openalex.org/W4401863510","doi":"https://doi.org/10.1145/3637528.3671650","title":"Understanding the Weakness of Large Language Model Agents within a Complex Android Environment","display_name":"Understanding the Weakness of Large Language Model Agents within a Complex Android Environment","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401863510","doi":"https://doi.org/10.1145/3637528.3671650"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671650","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671650","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671650","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671650","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5060626806","display_name":"Mingzhe Xing","orcid":"https://orcid.org/0000-0002-2065-9852"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingzhe Xing","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061105350","display_name":"Rongkai Zhang","orcid":"https://orcid.org/0009-0003-1652-7202"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rongkai Zhang","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050108117","display_name":"Hui Xue","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hui Xue","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070766481","display_name":"Qi Chen","orcid":"https://orcid.org/0009-0006-7394-0185"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Chen","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346602","display_name":"Fan Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102979232","display_name":"Zhen Xiao","orcid":"https://orcid.org/0000-0002-6784-9709"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Xiao","raw_affiliation_strings":["Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5060626806"],"corresponding_institution_ids":["https://openalex.org/I20231570"],"apc_list":null,"apc_paid":null,"fwci":4.3884,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.95056488,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"6061","last_page":"6072"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9926000237464905,"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/T10028","display_name":"Topic Modeling","score":0.9926000237464905,"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/T10260","display_name":"Software Engineering Research","score":0.9699000120162964,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9539999961853027,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/computer-science","display_name":"Computer science","score":0.8179343938827515},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6364689469337463},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6172425150871277},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.4426805078983307},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.436749666929245},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.38493067026138306},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3611418604850769},{"id":"https://openalex.org/keywords/risk-analysis","display_name":"Risk analysis (engineering)","score":0.32144230604171753}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8179343938827515},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6364689469337463},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6172425150871277},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.4426805078983307},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.436749666929245},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38493067026138306},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3611418604850769},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.32144230604171753},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671650","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671650","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671650","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3637528.3671650","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3637528.3671650","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3637528.3671650","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4401863510.pdf","grobid_xml":"https://content.openalex.org/works/W4401863510.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W317957491","https://openalex.org/W3164797848","https://openalex.org/W4242962246","https://openalex.org/W4385566059","https://openalex.org/W4389518737","https://openalex.org/W4393065402","https://openalex.org/W4396758667"],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"have":[4],"empowered":[5],"intelligent":[6],"agents":[7,31,48,72,100,146],"to":[8,23,49,74,97,118,132,153,207],"execute":[9],"intricate":[10],"tasks":[11,60],"within":[12],"domain-specific":[13],"software":[14,25],"such":[15,82],"as":[16,83,171],"browsers":[17],"and":[18,42,54,86,94,115,129,151,169,190,218,232],"games.":[19],"However,":[20],"when":[21],"applied":[22],"general-purpose":[24],"systems":[26],"like":[27],"operating":[28,104],"systems,":[29],"LLM":[30,47,69,99,145,178,216],"face":[32],"three":[33],"primary":[34,172],"challenges.":[35],"Firstly,":[36],"the":[37,120,123,134,175,186,192,205],"action":[38],"space":[39],"is":[40,204],"vast":[41],"dynamic,":[43],"posing":[44],"difficulties":[45],"for":[46,174,223,235],"maintain":[50],"an":[51,92],"up-to-date":[52],"understanding":[53,212],"deliver":[55],"accurate":[56,128],"responses.":[57],"Secondly,":[58],"real-world":[59],"often":[61],"require":[62],"inter-application":[63],"cooperation,":[64],"demanding":[65],"farsighted":[66],"planning":[67],"from":[68],"agents.":[70,179],"Thirdly,":[71],"need":[73],"identify":[75,158],"optimal":[76],"solutions":[77],"aligning":[78],"with":[79,197],"user":[80],"constraints,":[81],"security":[84],"concerns":[85],"preferences.":[87],"These":[88],"challenges":[89],"motivate":[90],"AndroidArena,":[91],"environment":[93],"benchmark":[95],"designed":[96],"evaluate":[98],"on":[101,185],"a":[102,113,159,220],"modern":[103],"system.":[105],"To":[106],"address":[107,133],"high-cost":[108],"of":[109,136,161,177,188,215],"manpower,":[110],"we":[111,157,181],"design":[112],"scalable":[114],"semi-automated":[116],"method":[117],"construct":[119],"benchmark.":[121],"In":[122],"task":[124],"evaluation,":[125],"AndroidArena":[126,236],"incorporates":[127],"adaptive":[130],"metrics":[131],"issue":[135],"non-unique":[137],"solutions.":[138],"Our":[139],"findings":[140],"reveal":[141],"that":[142],"even":[143],"state-of-the-art":[144],"struggle":[147],"in":[148,211,226],"cross-APP":[149],"scenarios":[150],"adhering":[152],"specific":[154],"constraints.":[155],"Additionally,":[156],"lack":[160],"four":[162],"key":[163],"capabilities,":[164],"i.e.":[165],"understanding,":[166],"reasoning,":[167],"exploration,":[168],"reflection,":[170,189],"reasons":[173],"failure":[176,187],"Furthermore,":[180],"provide":[182],"empirical":[183],"analysis":[184],"improve":[191],"success":[193],"rate":[194],"by":[195],"27%":[196],"our":[198],"proposed":[199],"exploration":[200],"strategy.":[201],"This":[202],"work":[203],"first":[206],"present":[208],"valuable":[209],"insights":[210],"fine-grained":[213],"weakness":[214],"agents,":[217],"offers":[219],"path":[221],"forward":[222],"future":[224],"research":[225],"this":[227],"area.":[228],"Environment,":[229],"benchmark,":[230],"prompt,":[231],"evaluation":[233],"code":[234],"are":[237],"released":[238],"at":[239],"https://github.com/AndroidArenaAgent/AndroidArena.":[240]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":11}],"updated_date":"2026-04-15T08:11:43.952461","created_date":"2025-10-10T00:00:00"}