{"id":"https://openalex.org/W7128506643","doi":"https://doi.org/10.48550/arxiv.2602.08023","title":"CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking","display_name":"CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking","publication_year":2026,"publication_date":"2026-02-08","ids":{"openalex":"https://openalex.org/W7128506643","doi":"https://doi.org/10.48550/arxiv.2602.08023"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.08023","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.08023","pdf_url":"https://arxiv.org/pdf/2602.08023","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.08023","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5001530440","display_name":"Nanda Rani","orcid":"https://orcid.org/0000-0003-1255-5284","observed_orcids":["https://orcid.org/0000-0003-1255-5284"]},"institutions":[{"id":"https://openalex.org/I4210128801","display_name":"Helmholtz Center for Information Security","ror":"https://ror.org/02njgxr09","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I4210128801"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Rani, Nanda","raw_affiliation_strings":["CISPA -Helmholtz Center for Information Security"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CISPA -Helmholtz Center for Information Security","institution_ids":["https://openalex.org/I4210128801"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099097255","display_name":"Kimberly Milner","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Milner, Kimberly","raw_affiliation_strings":["NYU Tandon School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Tandon School of Engineering","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113123602","display_name":"Minghao Shao","orcid":"https://orcid.org/0009-0002-4467-6224","observed_orcids":["https://orcid.org/0009-0002-4467-6224","https://orcid.org/0009-0003-6060-5693"]},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Shao, Minghao","raw_affiliation_strings":["NYU Abu Dhabi","NYU Tandon School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Abu Dhabi","institution_ids":["https://openalex.org/I120250893","https://openalex.org/I57206974"]},{"raw_affiliation_string":"NYU Tandon School of Engineering","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007457263","display_name":"Meet Udeshi","orcid":"https://orcid.org/0000-0001-7297-0880","observed_orcids":["https://orcid.org/0000-0001-7297-0880"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Udeshi, Meet","raw_affiliation_strings":["NYU Tandon School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Tandon School of Engineering","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101377025","display_name":"Haoran Xi","orcid":"https://orcid.org/0009-0005-3268-7366","observed_orcids":["https://orcid.org/0009-0005-3268-7366","https://orcid.org/0009-0009-3051-1630"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xi, Haoran","raw_affiliation_strings":["NYU Tandon School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Tandon School of Engineering","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068986465","display_name":"Venkata Sai Charan Putrevu","orcid":"https://orcid.org/0000-0003-4535-8690","observed_orcids":["https://orcid.org/0000-0003-4535-8690"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Putrevu, Venkata Sai Charan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063578033","display_name":"Saksham Aggarwal","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aggarwal, Saksham","raw_affiliation_strings":["NYU Tandon School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Tandon School of Engineering","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125509541","display_name":"Sandeep K. Shukla","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I64189192","display_name":"International Institute of Information Technology, Hyderabad","ror":"https://ror.org/05f11g639","country_code":"IN","type":"education","lineage":["https://openalex.org/I64189192"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shukla, Sandeep K.","raw_affiliation_strings":["IIIT Hyderabad"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIT Hyderabad","institution_ids":["https://openalex.org/I64189192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054769060","display_name":"P. Krishnamurthy","orcid":"https://orcid.org/0000-0001-8264-7972","observed_orcids":["https://orcid.org/0000-0001-8264-7972"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishnamurthy, Prashanth","raw_affiliation_strings":["NYU Tandon School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Tandon School of Engineering","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082413942","display_name":"Farshad Khorrami","orcid":"https://orcid.org/0000-0002-8418-004X","observed_orcids":["https://orcid.org/0000-0002-8418-004X"]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khorrami, Farshad","raw_affiliation_strings":["NYU Tandon School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Tandon School of Engineering","institution_ids":["https://openalex.org/I57206974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125525937","display_name":"Muhammad Shafique","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I120250893","display_name":"New York University Abu Dhabi","ror":"https://ror.org/00e5k0821","country_code":"AE","type":"education","lineage":["https://openalex.org/I120250893","https://openalex.org/I57206974"]},{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Shafique, Muhammad","raw_affiliation_strings":["NYU Abu Dhabi"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Abu Dhabi","institution_ids":["https://openalex.org/I120250893","https://openalex.org/I57206974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124020384","display_name":"Ramesh Karri","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I57206974","display_name":"New York University","ror":"https://ror.org/0190ak572","country_code":"US","type":"education","lineage":["https://openalex.org/I57206974"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Karri, Ramesh","raw_affiliation_strings":["NYU Tandon School of Engineering"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NYU Tandon School of Engineering","institution_ids":["https://openalex.org/I57206974"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.6996999979019165,"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.6996999979019165,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.18029999732971191,"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":0.059300001710653305,"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/capture-the-flag","display_name":"Capture the Flag","score":0.6710000038146973},{"id":"https://openalex.org/keywords/web-application-vulnerabilities","display_name":"web application vulnerabilities","score":0.5799999833106995},{"id":"https://openalex.org/keywords/target-prioritization","display_name":"target prioritization","score":0.7400000095367432},{"id":"https://openalex.org/keywords/multi-agent-systems","display_name":"multi-agent systems","score":0.640999972820282},{"id":"https://openalex.org/keywords/reasoning-traces","display_name":"reasoning traces","score":0.9020000100135803}],"concepts":[{"id":"https://openalex.org/C176856949","wikidata":"https://www.wikidata.org/wiki/Q2001676","display_name":"Offensive","level":2,"score":0.90420001745224},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7452999949455261},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.6869999766349792},{"id":"https://openalex.org/C95713431","wikidata":"https://www.wikidata.org/wiki/Q631425","display_name":"Vulnerability (computing)","level":2,"score":0.6829000115394592},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.6614000201225281},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6503999829292297},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5407000184059143},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.37059998512268066},{"id":"https://openalex.org/C167063184","wikidata":"https://www.wikidata.org/wiki/Q1400839","display_name":"Vulnerability assessment","level":3,"score":0.3495999872684479},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.3458999991416931},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.33640000224113464},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C140547941","wikidata":"https://www.wikidata.org/wiki/Q7797194","display_name":"Threat model","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C2776576444","wikidata":"https://www.wikidata.org/wiki/Q303569","display_name":"Attack surface","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.26910001039505005},{"id":"https://openalex.org/C35578498","wikidata":"https://www.wikidata.org/wiki/Q193424","display_name":"Web service","level":2,"score":0.25760000944137573},{"id":"https://openalex.org/C65856478","wikidata":"https://www.wikidata.org/wiki/Q3991682","display_name":"Attack model","level":2,"score":0.2556999921798706}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.08023","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.08023","pdf_url":"https://arxiv.org/pdf/2602.08023","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.2602.08023","doi":"https://doi.org/10.48550/arxiv.2602.08023","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.08023","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:2602.08023","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2602.08023","pdf_url":"https://arxiv.org/pdf/2602.08023","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7128506643.pdf","grobid_xml":"https://content.openalex.org/works/W7128506643.grobid-xml"},"referenced_works_count":15,"referenced_works":["https://openalex.org/W4391987669","https://openalex.org/W4402502904","https://openalex.org/W4403788084","https://openalex.org/W4405035082","https://openalex.org/W4405073917","https://openalex.org/W4407687097","https://openalex.org/W4415159865","https://openalex.org/W4416982487","https://openalex.org/W4417134203","https://openalex.org/W4417348357","https://openalex.org/W6910476441","https://openalex.org/W6929387203","https://openalex.org/W7136296626","https://openalex.org/W7138370235","https://openalex.org/W7197012116"],"related_works":["https://openalex.org/W7138370235","https://openalex.org/W7161035179","https://openalex.org/W7204526542","https://openalex.org/W7162107299","https://openalex.org/W4407687097","https://openalex.org/W7155212644","https://openalex.org/W7130581202","https://openalex.org/W7166575371","https://openalex.org/W7155246080","https://openalex.org/W7128094579"],"abstract_inverted_index":{"Existing":[0],"benchmarks":[1],"for":[2,123],"LLM-based":[3],"offensive":[4,62],"security":[5,63,150],"agents":[6,72,89,137],"use":[7],"isolated,":[8],"single-target":[9],"setups":[10],"with":[11],"a":[12,57,66,85,103,108],"known":[13],"vulnerable":[14,82],"service":[15],"and":[16,35,75,94,112,148],"fixed":[17],"objective.":[18],"They":[19],"measure":[20],"exploitation":[21,49],"effectively,":[22],"but":[23],"miss":[24],"how":[25,71,136],"real":[26],"Capture-the-Flag":[27],"(CTF)":[28],"participants":[29],"triage":[30],"unknown":[31],"surfaces,":[32],"prioritize":[33],"targets,":[34],"allocate":[36],"effort":[37],"under":[38],"uncertainty.":[39],"Current":[40],"evaluations":[41],"therefore":[42],"fail":[43],"to":[44],"assess":[45],"strategic":[46],"reasoning":[47,121],"beyond":[48,130],"alone.":[50],"To":[51],"address":[52],"this,":[53],"we":[54],"introduce":[55],"\\textit{CTFExplorer},":[56],"benchmark":[58],"suite":[59],"that":[60,118],"shifts":[61],"evaluation":[64,116,129],"toward":[65],"multi-target":[67],"setting,":[68],"which":[69],"tests":[70],"explore,":[73],"prioritize,":[74],"chain":[76],"attacks.":[77],"CTFExplorer":[78],"deploys":[79],"40":[80],"web-based":[81],"services":[83],"within":[84],"single":[86],"environment,":[87],"where":[88],"must":[90],"autonomously":[91],"discover,":[92],"distinguish,":[93],"exploit":[95],"targets":[96],"without":[97],"predefined":[98],"guidance.":[99],"We":[100],"also":[101],"present":[102],"reactive":[104],"multi-agent":[105],"setup":[106],"as":[107,135],"reference":[109],"agent":[110],"framework":[111,117],"develop":[113],"an":[114],"agent-agnostic":[115],"records":[119],"structured":[120],"traces":[122],"fine-grained":[124],"assessment.":[125],"This":[126],"enables":[127],"behavioral":[128],"binary":[131],"flag":[132],"capture,":[133],"such":[134],"manage":[138],"target":[139],"selection,":[140],"handle":[141],"failed":[142],"hypotheses,":[143],"coordinate":[144],"across":[145],"multiple":[146],"stages,":[147],"extract":[149],"intelligence.":[151]},"counts_by_year":[{"year":2026,"cited_by_count":4}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-02-11T00:00:00"}
