{"id":"https://openalex.org/W7156159401","doi":"https://doi.org/10.1145/3774904.3792215","title":"ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks","display_name":"ColorBench: Benchmarking Mobile Agents with Graph-Structured Framework for Complex Long-Horizon Tasks","publication_year":2026,"publication_date":"2026-04-12","ids":{"openalex":"https://openalex.org/W7156159401","doi":"https://doi.org/10.1145/3774904.3792215"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792215","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792215","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792215","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5134692348","display_name":"Yuanyi Song","orcid":"https://orcid.org/0009-0007-7731-1332"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanyi Song","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0009-0007-7731-1332","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102765219","display_name":"Heyuan Huang","orcid":"https://orcid.org/0000-0002-9351-1285"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Heyuan Huang","raw_affiliation_strings":["OPPO, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0000-0320-3629","affiliations":[{"raw_affiliation_string":"OPPO, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082755201","display_name":"Qiqiang Lin","orcid":"https://orcid.org/0000-0002-8587-1651"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiqiang Lin","raw_affiliation_strings":["OPPO, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8587-1651","affiliations":[{"raw_affiliation_string":"OPPO, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045914285","display_name":"Yin Zhao","orcid":"https://orcid.org/0000-0002-1470-7184"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yin Zhao","raw_affiliation_strings":["OPPO, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0002-5842-129X","affiliations":[{"raw_affiliation_string":"OPPO, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107124382","display_name":"Xiangmou Qu","orcid":"https://orcid.org/0009-0006-4449-522X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangmou Qu","raw_affiliation_strings":["OPPO, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0006-4449-522X","affiliations":[{"raw_affiliation_string":"OPPO, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134729584","display_name":"Jun Wang","orcid":"https://orcid.org/0009-0005-2577-6221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["OPPO, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0005-2577-6221","affiliations":[{"raw_affiliation_string":"OPPO, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033117282","display_name":"Xingyu Lou","orcid":"https://orcid.org/0009-0003-3180-0668"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xingyu Lou","raw_affiliation_strings":["OPPO, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0003-3180-0668","affiliations":[{"raw_affiliation_string":"OPPO, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107807658","display_name":"Liu W","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weiwen Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9148-3997","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070962435","display_name":"Zhuosheng Zhang","orcid":"https://orcid.org/0000-0002-4183-3645"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuosheng Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-4183-3645","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5134729584","display_name":"Jun Wang","orcid":"https://orcid.org/0009-0005-2577-6221"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jun Wang","raw_affiliation_strings":["OPPO, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-0481-5341","affiliations":[{"raw_affiliation_string":"OPPO, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122751277","display_name":"Zhaoxiang Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhaoxiang Wang","raw_affiliation_strings":["OPPO, Shenzhen, China"],"raw_orcid":"https://orcid.org/0009-0007-4925-7703","affiliations":[{"raw_affiliation_string":"OPPO, Shenzhen, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064534815","display_name":"Yong Yu","orcid":"https://orcid.org/0000-0003-4457-2820"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Yu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4457-2820","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441502","display_name":"Wei Zhang","orcid":"https://orcid.org/0000-0001-7800-3189"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weinan Zhang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0127-2425","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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":"7024","last_page":"7035"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.12710000574588776,"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"}},"topics":[{"id":"https://openalex.org/T14347","display_name":"Big Data and Digital Economy","score":0.12710000574588776,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.05420000106096268,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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":0.04520000144839287,"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/benchmarking","display_name":"Benchmarking","score":0.8622000217437744},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7598000168800354},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.6154000163078308},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5895000100135803},{"id":"https://openalex.org/keywords/mobile-device","display_name":"Mobile device","score":0.5078999996185303},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.37310001254081726},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.34869998693466187}],"concepts":[{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.8622000217437744},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7608000040054321},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7598000168800354},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.6154000163078308},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5895000100135803},{"id":"https://openalex.org/C186967261","wikidata":"https://www.wikidata.org/wiki/Q5082128","display_name":"Mobile device","level":2,"score":0.5078999996185303},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3928999900817871},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37310001254081726},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.35850000381469727},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33709999918937683},{"id":"https://openalex.org/C144543869","wikidata":"https://www.wikidata.org/wiki/Q2738570","display_name":"Mobile computing","level":2,"score":0.3353999853134155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29989999532699585},{"id":"https://openalex.org/C2780102126","wikidata":"https://www.wikidata.org/wiki/Q10928179","display_name":"Online and offline","level":2,"score":0.29789999127388},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2976999878883362},{"id":"https://openalex.org/C2777851325","wikidata":"https://www.wikidata.org/wiki/Q7094102","display_name":"Online model","level":2,"score":0.2953999936580658},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28870001435279846},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C95491727","wikidata":"https://www.wikidata.org/wiki/Q992968","display_name":"Mobile telephony","level":3,"score":0.27630001306533813}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792215","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792215","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792215","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792215","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W2765874585","https://openalex.org/W2891350705","https://openalex.org/W3206316161","https://openalex.org/W4399121418","https://openalex.org/W4402753874","https://openalex.org/W4409767398","https://openalex.org/W4413145552"],"related_works":[],"abstract_inverted_index":{"The":[0],"rapid":[1],"advancement":[2],"of":[3,70,116,135,159],"multimodal":[4],"large":[5],"language":[6],"models":[7],"has":[8],"enabled":[9],"agents":[10],"to":[11],"operate":[12],"mobile":[13,26,30,44],"devices":[14],"by":[15,65],"directly":[16],"interacting":[17],"with":[18,155],"graphical":[19],"user":[20],"interfaces,":[21],"opening":[22],"new":[23],"possibilities":[24],"for":[25,37,77],"automation.":[27],"However,":[28],"real-world":[29],"tasks":[31,150],"are":[32],"often":[33],"complex":[34,129],"and":[35,68,88,91,143,171],"allow":[36],"multiple":[38,136],"valid":[39,137],"solutions.":[40],"This":[41],"contradicts":[42],"current":[43],"agent":[45,80],"evaluation":[46,90,134],"standards:":[47],"offline":[48,87],"static":[49,114],"benchmarks":[50],"can":[51],"only":[52],"validate":[53],"a":[54,98,125],"single":[55],"predefined":[56],"''golden":[57],"path'',":[58],"while":[59],"online":[60,89],"dynamic":[61,117],"testing":[62,93],"is":[63],"constrained":[64],"the":[66,84,105],"complexity":[67],"non-reproducibility":[69],"real":[71],"devices,":[72],"making":[73],"both":[74],"approaches":[75],"inadequate":[76],"comprehensively":[78],"assessing":[79],"capabilities.":[81],"To":[82],"bridge":[83],"gap":[85],"between":[86],"enhance":[92],"stability,":[94],"this":[95],"paper":[96],"introduces":[97],"novel":[99],"graph-structured":[100],"benchmarking":[101],"framework.":[102],"By":[103],"modeling":[104],"finite":[106],"states":[107],"observed":[108],"during":[109],"real-device":[110],"interactions,":[111],"it":[112],"achieves":[113],"simulation":[115],"behaviors.":[118],"Building":[119],"on":[120,128],"this,":[121],"we":[122],"develop":[123],"ColorBench,":[124],"benchmark":[126],"focused":[127],"long-horizon":[130],"tasks.":[131],"It":[132],"supports":[133],"solutions,":[138],"subtask":[139],"completion":[140],"rate":[141],"statistics,":[142],"atomic-level":[144],"capability":[145],"analysis.":[146],"ColorBench":[147],"contains":[148],"175":[149],"(74":[151],"single-app,":[152],"101":[153],"cross-app)":[154],"an":[156],"average":[157],"length":[158],"over":[160],"13":[161],"steps.":[162],"Each":[163],"task":[164],"includes":[165],"at":[166],"least":[167],"two":[168],"correct":[169],"paths":[170],"several":[172],"typical":[173],"error":[174],"paths,":[175],"enabling":[176],"quasi-dynamic":[177],"interaction.":[178]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-28T00:00:00"}
