{"id":"https://openalex.org/W4415190847","doi":"https://doi.org/10.48550/arxiv.2508.03923","title":"CoAct-1: Computer-using Multi-Agent System with Coding Actions","display_name":"CoAct-1: Computer-using Multi-Agent System with Coding Actions","publication_year":2025,"publication_date":"2025-08-05","ids":{"openalex":"https://openalex.org/W4415190847","doi":"https://doi.org/10.48550/arxiv.2508.03923"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2508.03923","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.03923","pdf_url":"https://arxiv.org/pdf/2508.03923","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2508.03923","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100701088","display_name":"Li Song","orcid":"https://orcid.org/0000-0003-2777-7576","observed_orcids":["https://orcid.org/0000-0003-2777-7576"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Song, Linxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114183949","display_name":"Yutong Dai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Yutong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110751285","display_name":"Viraj Prabhu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Prabhu, Viraj","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017743340","display_name":"Jieyu Zhang","orcid":"https://orcid.org/0000-0002-2827-3487","observed_orcids":["https://orcid.org/0000-0002-2827-3487"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jieyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113985908","display_name":"Taiwei Shi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Taiwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361041","display_name":"Li Li","orcid":"https://orcid.org/0000-0001-8485-2216","observed_orcids":["https://orcid.org/0000-0001-8485-2216","https://orcid.org/0009-0002-5241-569X","https://orcid.org/0009-0009-1268-6453"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Li","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100608757","display_name":"Junnan Li","orcid":"https://orcid.org/0000-0002-2781-0949","observed_orcids":["https://orcid.org/0000-0002-2781-0949"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Junnan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042646536","display_name":"Silvio Savarese","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Savarese, Silvio","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101631516","display_name":"Zeyuan Chen","orcid":"https://orcid.org/0000-0002-0286-6196","observed_orcids":["https://orcid.org/0000-0002-0286-6196","https://orcid.org/0009-0003-7610-9758"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Zeyuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066282713","display_name":"Jieyu Zhao","orcid":"https://orcid.org/0000-0002-1013-557X","observed_orcids":["https://orcid.org/0000-0002-1013-557X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Jieyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100687200","display_name":"Ran Xu","orcid":"https://orcid.org/0000-0003-1387-6696","observed_orcids":["https://orcid.org/0000-0003-1387-6696"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Ran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5032046813","display_name":"Caiming Xiong","orcid":"https://orcid.org/0000-0003-0349-8628","observed_orcids":["https://orcid.org/0000-0003-0349-8628"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiong, Caiming","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":1,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.8105000257492065,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.8105000257492065,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.027000000700354576,"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/T12031","display_name":"Speech and dialogue systems","score":0.011300000362098217,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.7979999780654907},{"id":"https://openalex.org/keywords/autonomous-agents","display_name":"autonomous agents","score":0.6909999847412109},{"id":"https://openalex.org/keywords/graphical-user-interface-interaction","display_name":"graphical user interface interaction","score":0.6830000281333923},{"id":"https://openalex.org/keywords/task-delegation","display_name":"task delegation","score":0.5569999814033508},{"id":"https://openalex.org/keywords/computer-automation","display_name":"computer automation","score":0.8240000009536743},{"id":"https://openalex.org/keywords/task-decomposition","display_name":"task decomposition","score":0.5270000100135803},{"id":"https://openalex.org/keywords/long-horizon-tasks","display_name":"long-horizon tasks","score":0.7379999756813049}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8341000080108643},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.6395000219345093},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.6252999901771545},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5817999839782715},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5072000026702881},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C37789001","wikidata":"https://www.wikidata.org/wiki/Q782543","display_name":"Graphical user interface","level":2,"score":0.37439998984336853},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.35440000891685486},{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.329800009727478},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.3208000063896179},{"id":"https://openalex.org/C2779038628","wikidata":"https://www.wikidata.org/wiki/Q7248497","display_name":"Programming by demonstration","level":3,"score":0.29989999532699585},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.2955999970436096},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28769999742507935},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.27079999446868896},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C17500928","wikidata":"https://www.wikidata.org/wiki/Q959968","display_name":"Control system","level":2,"score":0.2630999982357025},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.2581999897956848},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.25600001215934753},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.25380000472068787}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2508.03923","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.03923","pdf_url":"https://arxiv.org/pdf/2508.03923","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2508.03923","doi":"https://doi.org/10.48550/arxiv.2508.03923","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2508.03923","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":"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":"pmh:oai:arXiv.org:2508.03923","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2508.03923","pdf_url":"https://arxiv.org/pdf/2508.03923","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"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],"agents":[1,23,61],"that":[2,76,89,193],"operate":[3],"computers":[4],"via":[5],"Graphical":[6],"User":[7],"Interfaces":[8],"(GUIs)":[9],"often":[10],"struggle":[11],"with":[12,24,81],"efficiency":[13],"and":[14,47,57,107,130,205],"reliability":[15],"on":[16,144],"complex,":[17],"long-horizon":[18],"tasks.":[19],"While":[20],"augmenting":[21],"these":[22],"planners":[25],"can":[26,105],"improve":[27],"task":[28,179],"decomposition,":[29],"they":[30],"remain":[31],"constrained":[32],"by":[33],"the":[34,117,145,170],"inherent":[35],"limitations":[36],"of":[37,157,173],"performing":[38],"all":[39],"actions":[40],"through":[41],"GUI":[42,97,122,188],"manipulation,":[43],"leading":[44,187],"to":[45,62,93,119,176,180,184],"brittleness":[46],"inefficiency.":[48],"In":[49],"this":[50],"work,":[51],"we":[52],"introduce":[53],"a":[54,66,72,95,100,152,178,197,201],"more":[55,202],"robust":[56],"flexible":[58],"paradigm:":[59],"enabling":[60],"use":[63],"coding":[64,195],"as":[65,196],"enhanced":[67],"action.":[68],"We":[69,140],"present":[70],"CoAct-1,":[71],"novel":[73],"multi-agent":[74],"system":[75,143],"synergistically":[77],"combines":[78],"GUI-based":[79],"control":[80],"direct":[82],"programmatic":[83],"execution.":[84],"CoAct-1":[85,150],"features":[86],"an":[87],"Orchestrator":[88],"dynamically":[90],"delegates":[91],"subtasks":[92],"either":[94],"conventional":[96],"Operator":[98],"or":[99,110],"specialized":[101],"Programmer":[102],"agent,":[103],"which":[104],"write":[106],"execute":[108],"Python":[109],"Bash":[111],"scripts.":[112],"This":[113],"hybrid":[114],"approach":[115,165],"allows":[116],"agent":[118],"bypass":[120],"inefficient":[121],"action":[123,199],"sequences":[124],"for":[125,186],"tasks":[126],"like":[127],"file":[128],"management":[129],"data":[131],"processing,":[132],"while":[133],"still":[134],"leveraging":[135],"visual":[136],"interaction":[137],"when":[138],"necessary.":[139],"evaluate":[141],"our":[142,164],"challenging":[146],"OSWorld":[147],"benchmark,":[148],"where":[149],"achieves":[151],"new":[153],"state-of-the-art":[154],"success":[155],"rate":[156],"60.76%,":[158],"significantly":[159],"outperforming":[160],"prior":[161],"methods.":[162],"Furthermore,":[163],"dramatically":[166],"improves":[167],"efficiency,":[168],"reducing":[169],"average":[171],"number":[172],"steps":[174],"required":[175],"complete":[177],"just":[181],"10.15,":[182],"compared":[183],"15":[185],"agents.":[189],"Our":[190],"results":[191],"demonstrate":[192],"integrating":[194],"core":[198],"provides":[200],"powerful,":[203],"efficient,":[204],"scalable":[206],"path":[207],"toward":[208],"generalized":[209],"computer":[210],"automation.":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-10-14T16:39:01.820549","created_date":"2025-10-15T00:00:00"}
