{"id":"https://openalex.org/W7204206972","doi":"https://doi.org/10.48550/arxiv.2608.23181","title":"CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild","display_name":"CyberFactory: Scaling Cyber Security Capabilities with Instances from the Wild","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204206972","doi":"https://doi.org/10.48550/arxiv.2608.23181"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23181","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23181","pdf_url":"https://arxiv.org/pdf/2608.23181","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/2608.23181","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148175554","display_name":"Jian Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Jian","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007865421","display_name":"Haau-Sing Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Haau-Sing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104317841","display_name":"Shawn Guo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guo, Shawn","raw_affiliation_strings":["IQuest Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IQuest Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148051624","display_name":"Zixi Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhao, Zixi","raw_affiliation_strings":["IQuest Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IQuest Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148104281","display_name":"Yibo Tan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tan, Yibo","raw_affiliation_strings":["IQuest Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IQuest Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148095472","display_name":"Jiajun Wu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wu, Jiajun","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5143344230","display_name":"Aishan Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Aishan","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148068281","display_name":"Xianglong Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Zhoujun","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129944627","display_name":"Xianglong Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Xianglong","raw_affiliation_strings":["Beihang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beihang University","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101578269","display_name":"Tianyu Zheng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Tianyu","raw_affiliation_strings":["IQuest Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IQuest Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121665631","display_name":"Bryan Dai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dai, Bryan","raw_affiliation_strings":["IQuest Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IQuest Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5148186132","display_name":"Chengran Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I79891267","display_name":"Singapore Management University","ror":"https://ror.org/050qmg959","country_code":"SG","type":"education","lineage":["https://openalex.org/I79891267"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yang, Chengran","raw_affiliation_strings":["Singapore Management University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Singapore Management University","institution_ids":["https://openalex.org/I79891267"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130208175","display_name":"Weifeng Lv","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lv, Weifeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5234000086784363,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.5234000086784363,"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/T10734","display_name":"Information and Cyber Security","score":0.23770000040531158,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.05590000003576279,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/vulnerability-patching","display_name":"vulnerability patching","score":0.7319999933242798},{"id":"https://openalex.org/keywords/trajectory-generation","display_name":"trajectory generation","score":0.5640000104904175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7677000164985657},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.6675000190734863},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5688999891281128},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.5649999976158142},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5095999836921692},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5087000131607056},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4555000066757202},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.44600000977516174},{"id":"https://openalex.org/C85847156","wikidata":"https://www.wikidata.org/wiki/Q59015987","display_name":"Verifiable secret sharing","level":3,"score":0.436599999666214},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.4196999967098236},{"id":"https://openalex.org/C147346212","wikidata":"https://www.wikidata.org/wiki/Q5492632","display_name":"Trusted computing base","level":4,"score":0.37299999594688416},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.36739999055862427},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.34630000591278076},{"id":"https://openalex.org/C2778571376","wikidata":"https://www.wikidata.org/wiki/Q1355821","display_name":"Frontier","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C2780264999","wikidata":"https://www.wikidata.org/wiki/Q7445032","display_name":"Security domain","level":2,"score":0.32919999957084656},{"id":"https://openalex.org/C2777042776","wikidata":"https://www.wikidata.org/wiki/Q4583103","display_name":"Preparedness","level":2,"score":0.3043999969959259},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3010999858379364},{"id":"https://openalex.org/C184356942","wikidata":"https://www.wikidata.org/wiki/Q830382","display_name":"Best practice","level":2,"score":0.2973000109195709},{"id":"https://openalex.org/C2780795517","wikidata":"https://www.wikidata.org/wiki/Q6030997","display_name":"Information assurance","level":3,"score":0.2937999963760376},{"id":"https://openalex.org/C521332185","wikidata":"https://www.wikidata.org/wiki/Q185816","display_name":"Analogy","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C121822524","wikidata":"https://www.wikidata.org/wiki/Q5157582","display_name":"Computer security model","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.28780001401901245},{"id":"https://openalex.org/C541664917","wikidata":"https://www.wikidata.org/wiki/Q14001","display_name":"Malware","level":2,"score":0.28369998931884766},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.2770000100135803},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C167063184","wikidata":"https://www.wikidata.org/wiki/Q1400839","display_name":"Vulnerability assessment","level":3,"score":0.2630999982357025},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.26010000705718994},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.2587999999523163},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C191267431","wikidata":"https://www.wikidata.org/wiki/Q911932","display_name":"Honeypot","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C207267971","wikidata":"https://www.wikidata.org/wiki/Q120208","display_name":"Emerging technologies","level":2,"score":0.25270000100135803},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23181","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23181","pdf_url":"https://arxiv.org/pdf/2608.23181","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.2608.23181","doi":"https://doi.org/10.48550/arxiv.2608.23181","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23181","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.23181","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23181","pdf_url":"https://arxiv.org/pdf/2608.23181","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":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, justice, and strong institutions","score":0.413611501455307}],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204206972.pdf","grobid_xml":"https://content.openalex.org/works/W7204206972.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7223557358","https://openalex.org/W6891827332","https://openalex.org/W4402502904","https://openalex.org/W7202148270","https://openalex.org/W6929387203","https://openalex.org/W7154606467","https://openalex.org/W7133506238","https://openalex.org/W4409190341","https://openalex.org/W4414891861","https://openalex.org/W7126227985"],"abstract_inverted_index":{"As":[0],"large":[1],"language":[2],"models":[3,37],"(LLMs)":[4],"continue":[5],"to":[6,118,151],"advance":[7],"in":[8,13,163],"coding":[9],"capabilities,":[10],"their":[11],"potential":[12],"cybersecurity":[14,27,42,91],"has":[15],"drawn":[16],"increasing":[17],"research":[18],"attention,":[19],"with":[20,127,141],"closed-source":[21],"LLMs":[22],"(e.g.,":[23],"Mythos)":[24],"delivering":[25],"advanced":[26],"capabilities.":[28],"However,":[29],"existing":[30],"open-source":[31,45,73],"efforts":[32],"remain":[33],"limited:":[34],"frontier":[35],"open-weight":[36],"do":[38],"not":[39],"provide":[40],"reproducible":[41],"training":[43,46,83],"solutions,":[44],"solutions":[47,149],"focus":[48],"on":[49],"isolated":[50],"tasks":[51],"and":[52,57,81,90,107,130,143,146,159,171,212],"lack":[53],"scalable":[54],"agentic":[55,59],"data,":[56],"scaling":[58],"rollouts":[60],"requires":[61],"strong":[62],"domain":[63,128],"priors.":[64],"In":[65],"this":[66],"work,":[67],"we":[68,157],"introduce":[69],"\\textbf{CyberFactory},":[70],"a":[71,114,200],"unified":[72],"framework":[74],"that":[75],"connects":[76],"data":[77],"construction,":[78],"trajectory":[79],"synthesis,":[80],"model":[82,139,208],"across":[84],"proof-of-concept":[85],"(PoC)":[86],"generation,":[87],"vulnerability":[88,98],"patching,":[89],"question":[92],"answering":[93],"(CyberQA).":[94],"CyberFactory":[95],"transforms":[96],"public":[97],"artifacts,":[99],"including":[100],"CVEs":[101],"from":[102],"the":[103,120,138,166,173,176,183,188,214,219],"wild,":[104],"into":[105],"executable":[106],"verifiable":[108],"task":[109],"instances.":[110],"It":[111],"further":[112],"uses":[113],"reusable":[115],"vulnerability-analysis":[116],"skill":[117,189],"guide":[119],"teacher":[121],"through":[122],"source":[123],"inspection,":[124],"problem":[125],"solving":[126],"prior,":[129],"evidence-based":[131],"validation.":[132],"The":[133],"resulting":[134],"supervision":[135],"is":[136],"agentic:":[137],"interacts":[140],"tools":[142],"target":[144],"environments":[145],"revises":[147],"its":[148,205],"according":[150],"execution":[152],"feedback.":[153],"Using":[154],"these":[155],"trajectories,":[156],"train":[158],"release":[160],"\\modelname\\footnote{\\emph{Aegis}":[161],"is,":[162],"Greek":[164],"mythology,":[165],"protective":[167],"shield":[168],"of":[169],"Zeus":[170],"Athena;":[172],"name":[174],"reflects":[175],"model's":[177],"defensive,":[178],"security-oriented":[179],"purpose.},":[180],"which":[181],"internalizes":[182],"skill-guided":[184],"procedure":[185],"without":[186],"requiring":[187],"at":[190],"inference":[191],"time.":[192],"On":[193],"CyberGym,":[194],"\\modelname":[195],"reaches":[196],"52.4%":[197],"Pass@1":[198],"under":[199,218],"one-hour":[201],"budget,":[202],"improving":[203],"over":[204],"Qwen~3.5":[206],"base":[207],"by":[209],"+22.8":[210],"points":[211],"outperforming":[213],"evaluated":[215],"general-purpose":[216],"backbones":[217],"same":[220],"scaffold.":[221]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-26T00:00:00"}