{"id":"https://openalex.org/W7161737465","doi":"https://doi.org/10.48550/arxiv.2605.16883","title":"SE-GA: Memory-Augmented Self-Evolution for GUI Agents","display_name":"SE-GA: Memory-Augmented Self-Evolution for GUI Agents","publication_year":2026,"publication_date":"2026-05-16","ids":{"openalex":"https://openalex.org/W7161737465","doi":"https://doi.org/10.48550/arxiv.2605.16883"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.16883","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16883","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":null,"license_id":null,"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.2605.16883","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136469724","display_name":"Shilong Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Shilong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025153128","display_name":"Lanjun Wang","orcid":"https://orcid.org/0000-0002-7696-5330"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Lanjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136473098","display_name":"Zhuosheng Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Zhuosheng","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/T11574","display_name":"Artificial Intelligence in Games","score":0.148499995470047,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.148499995470047,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.12359999865293503,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07249999791383743,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/pipeline","display_name":"Pipeline (software)","score":0.6531000137329102},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.5457000136375427},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5422999858856201},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5407999753952026},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5157999992370605},{"id":"https://openalex.org/keywords/graphical-user-interface","display_name":"Graphical user interface","score":0.4474000036716461},{"id":"https://openalex.org/keywords/core","display_name":"Core (optical fiber)","score":0.43950000405311584},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.3837999999523163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7850000262260437},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6531000137329102},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.5457000136375427},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5422999858856201},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5407999753952026},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5157999992370605},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.4474000036716461},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44200000166893005},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.43950000405311584},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.3837999999523163},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.38199999928474426},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3693000078201294},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3156999945640564},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.31299999356269836},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C155846161","wikidata":"https://www.wikidata.org/wiki/Q1143367","display_name":"Graphical model","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.25870001316070557},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.2542000114917755},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2535000145435333},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.25040000677108765}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.16883","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16883","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.16883","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.16883","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"Graphical":[1],"User":[2],"Interface":[3],"(GUI)":[4],"agents":[5],"often":[6],"struggle":[7],"with":[8,46],"multi-step":[9],"tasks":[10],"due":[11],"to":[12,21,23,74,101,147],"constrained":[13],"context":[14],"windows":[15],"and":[16,71,103,114,129],"static":[17],"policies":[18],"that":[19,41,94],"fail":[20],"adapt":[22],"dynamic":[24,148],"environments.":[25,149],"To":[26,80],"address":[27],"these":[28],"limitations,":[29],"this":[30],"work":[31],"proposes":[32],"the":[33,52,96,105,132,140,144],"Self-Evolving":[34],"GUI":[35],"Agent":[36],"(SE-GA),":[37],"a":[38,91],"novel":[39],"framework":[40],"integrates":[42],"hierarchical":[43],"memory":[44],"structures":[45],"an":[47],"iterative":[48],"self-improvement":[49],"mechanism.":[50],"At":[51],"core":[53],"of":[54,125],"our":[55],"approach":[56],"is":[57,90],"Test-Time":[58],"Memory":[59],"Extension":[60],"(TTME),":[61],"which":[62,89],"facilitates":[63],"long-term":[64],"planning":[65],"by":[66,99],"dynamically":[67],"retrieving":[68],"episodic,":[69],"semantic,":[70],"experiential":[72],"memories":[73],"provide":[75],"salient":[76],"contexts":[77],"during":[78],"inference.":[79],"ensure":[81],"continuous":[82],"learning,":[83],"we":[84],"introduce":[85],"Memory-Augmented":[86],"Self-Evolution":[87],"(MASE),":[88],"training":[92],"pipeline":[93],"adopts":[95],"data":[97],"collected":[98],"TTME":[100],"stabilize":[102],"enhance":[104],"agent's":[106],"foundational":[107],"policy.":[108],"Extensive":[109],"evaluations":[110],"across":[111],"both":[112],"offline":[113],"online":[115],"benchmarks":[116],"demonstrate":[117],"SE-GA":[118],"achieves":[119],"state-of-the-art":[120],"performance,":[121],"reaching":[122],"success":[123],"rates":[124],"89.0\\%":[126],"on":[127,131,139],"ScreenSpot":[128],"75.8\\%":[130],"challenging":[133],"AndroidControl-High":[134],"dataset.":[135],"Furthermore,":[136],"significant":[137],"improvements":[138],"AndroidWorld":[141],"benchmark":[142],"highlight":[143],"superior":[145],"generalization":[146],"Open":[150],"source":[151],"code:":[152],"https://github.com/jinshilong-dev/SE-GA":[153]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-20T00:00:00"}