{"id":"https://openalex.org/W7128556164","doi":null,"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/W7128556164"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2602.08023","is_oa":true,"landing_page_url":"http://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":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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv"],"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":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rani, Nanda","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099097255","display_name":"Kimberly Milner","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Milner, Kimberly","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113123602","display_name":"Minghao Shao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shao, Minghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007457263","display_name":"Meet Udeshi","orcid":"https://orcid.org/0000-0001-7297-0880"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Udeshi, Meet","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101377025","display_name":"Haoran Xi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xi, Haoran","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068986465","display_name":"Venkata Sai Charan Putrevu","orcid":"https://orcid.org/0000-0003-3495-8332"},"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},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Aggarwal, Saksham","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125509541","display_name":"Sandeep K. Shukla","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shukla, Sandeep K.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5122904653","display_name":"Prashanth Krishnamurthy","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Krishnamurthy, Prashanth","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082413942","display_name":"Farshad Khorrami","orcid":"https://orcid.org/0000-0002-8418-004X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khorrami, Farshad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125525937","display_name":"Muhammad Shafique","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shafique, Muhammad","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125574657","display_name":"Ramesh Karri","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Karri, Ramesh","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":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/T10734","display_name":"Information and Cyber Security","score":0.45500001311302185,"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/T10734","display_name":"Information and Cyber Security","score":0.45500001311302185,"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/T10400","display_name":"Network Security and Intrusion Detection","score":0.23250000178813934,"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"}},{"id":"https://openalex.org/T11807","display_name":"Infrastructure Resilience and Vulnerability Analysis","score":0.0560000017285347,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/offensive","display_name":"Offensive","score":0.90420001745224},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7452999949455261},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.6869999766349792},{"id":"https://openalex.org/keywords/vulnerability","display_name":"Vulnerability (computing)","score":0.6829000115394592},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5407000184059143},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.37059998512268066},{"id":"https://openalex.org/keywords/vulnerability-assessment","display_name":"Vulnerability assessment","score":0.3495999872684479}],"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","is_oa":true,"landing_page_url":"http://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":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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:arXiv.org:2602.08023","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":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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.08023","is_oa":true,"landing_page_url":"http://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":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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"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":{"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":[],"updated_date":"2026-07-03T08:13:44.112507","created_date":"2026-02-11T00:00:00"}
