{"id":"https://openalex.org/W7172011000","doi":"https://doi.org/10.48550/arxiv.2607.28520","title":"Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation","display_name":"Agents That Certify Their Own Exploits: Confidence-Scheduled Restricted Responses for Safe Opponent Exploitation","publication_year":2026,"publication_date":"2026-07-30","ids":{"openalex":"https://openalex.org/W7172011000","doi":"https://doi.org/10.48550/arxiv.2607.28520"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2607.28520","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.28520","pdf_url":"https://arxiv.org/pdf/2607.28520","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/2607.28520","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Li, Boning","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Boning","raw_affiliation_strings":["IIIS , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIS , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5144117690","display_name":"Longbo Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang, Longbo","raw_affiliation_strings":["IIIS , Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IIIS , Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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":0.9922000169754028,"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":0.9922000169754028,"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/T11031","display_name":"Game Theory and Applications","score":0.00279999990016222,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.00139999995008111,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/confidence-sequences","display_name":"confidence sequences","score":0.5299999713897705},{"id":"https://openalex.org/keywords/nash-equilibrium","display_name":"Nash equilibrium","score":0.7480000257492065},{"id":"https://openalex.org/keywords/imperfect-information-games","display_name":"imperfect information games","score":0.8109999895095825},{"id":"https://openalex.org/keywords/zero-sum-games","display_name":"zero-sum games","score":0.7730000019073486},{"id":"https://openalex.org/keywords/safety-certificates","display_name":"safety certificates","score":0.3970000147819519},{"id":"https://openalex.org/keywords/best-response","display_name":"best response","score":0.3310000002384186}],"concepts":[{"id":"https://openalex.org/C41065033","wikidata":"https://www.wikidata.org/wiki/Q2825412","display_name":"Adversary","level":2,"score":0.7598999738693237},{"id":"https://openalex.org/C96865113","wikidata":"https://www.wikidata.org/wiki/Q2946816","display_name":"Certificate","level":2,"score":0.7242000102996826},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.6288999915122986},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6251999735832214},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6202999949455261},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.515999972820282},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4530999958515167},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.3970000147819519},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.39100000262260437},{"id":"https://openalex.org/C2778067643","wikidata":"https://www.wikidata.org/wiki/Q166507","display_name":"Interval (graph theory)","level":2,"score":0.3628999888896942},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3555000126361847},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3409999907016754},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.3384000062942505},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.3359000086784363},{"id":"https://openalex.org/C46814582","wikidata":"https://www.wikidata.org/wiki/Q23389","display_name":"Nash equilibrium","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29919999837875366},{"id":"https://openalex.org/C200594392","wikidata":"https://www.wikidata.org/wiki/Q812529","display_name":"Bayesian game","level":4,"score":0.27570000290870667},{"id":"https://openalex.org/C97399411","wikidata":"https://www.wikidata.org/wiki/Q825367","display_name":"Coin flipping","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.2694999873638153},{"id":"https://openalex.org/C32407928","wikidata":"https://www.wikidata.org/wiki/Q2733833","display_name":"Best response","level":3,"score":0.26499998569488525},{"id":"https://openalex.org/C159718280","wikidata":"https://www.wikidata.org/wiki/Q5526353","display_name":"Gas meter prover","level":3,"score":0.25270000100135803},{"id":"https://openalex.org/C202556891","wikidata":"https://www.wikidata.org/wiki/Q1584646","display_name":"Repeated game","level":3,"score":0.2524000108242035}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2607.28520","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.28520","pdf_url":"https://arxiv.org/pdf/2607.28520","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.2607.28520","doi":"https://doi.org/10.48550/arxiv.2607.28520","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.28520","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:2607.28520","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2607.28520","pdf_url":"https://arxiv.org/pdf/2607.28520","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7172011000.pdf","grobid_xml":"https://content.openalex.org/works/W7172011000.grobid-xml"},"referenced_works_count":9,"referenced_works":["https://openalex.org/W1525285119","https://openalex.org/W7123245009","https://openalex.org/W7134257309","https://openalex.org/W7158280075","https://openalex.org/W7160899370","https://openalex.org/W7160920688","https://openalex.org/W7161840774","https://openalex.org/W7162750138","https://openalex.org/W7171819697"],"related_works":["https://openalex.org/W7097898716","https://openalex.org/W2024561607","https://openalex.org/W7133230821","https://openalex.org/W2086594227","https://openalex.org/W3038653784","https://openalex.org/W2295179707","https://openalex.org/W4385261531","https://openalex.org/W4230995440","https://openalex.org/W7096812454","https://openalex.org/W3086114309"],"abstract_inverted_index":{"An":[0],"agent":[1,74],"playing":[2],"a":[3,7,23,29,43,71,107,124,129,137,150,160,201],"Nash-equilibrium":[4],"strategy":[5,78,209],"in":[6],"two-player":[8],"zero-sum":[9],"imperfect-information":[10],"game":[11,14],"secures":[12],"the":[13,18,63,73,77,167,175,181,185,197,216,221,235],"value":[15,20],"but":[16],"forfeits":[17],"additional":[19],"offered":[21],"by":[22,149],"flawed":[24],"opponent.":[25],"Diffuse":[26],"deviations":[27,122],"pose":[28],"particular":[30],"challenge:":[31],"binary":[32,203],"release":[33],"rules":[34],"may":[35],"gather":[36],"too":[37],"little":[38],"evidence":[39],"to":[40,47,88],"act,":[41],"while":[42,184,205],"full":[44],"best":[45,152],"response":[46],"an":[48,117],"incomplete":[49],"opponent":[50,126],"model":[51,178],"can":[52],"be":[53],"highly":[54],"exploitable.":[55],"We":[56],"introduce":[57],"\\emph{budget-constrained":[58],"confidence-scheduled":[59],"restricted":[60],"responses}":[61],"(CS-RNR),":[62],"first":[64],"opponent-exploitation":[65],"method":[66,96],"whose":[67],"safety":[68],"guarantee":[69],"is":[70,89,147,157,172],"certificate":[72,156,186,237],"computes":[75],"on":[76,174],"it":[79,86,91],"actually":[80],"deploys,":[81],"so":[82],"that":[83],"every":[84,207],"exploit":[85],"commits":[87],"one":[90],"has":[92],"audited":[93,232],"itself.":[94],"The":[95,120,154],"tracks":[97],"pooled":[98],"action":[99],"frequencies":[100],"with":[101,159,166],"anytime-valid":[102],"confidence":[103],"sequences":[104],"and":[105,163,227],"treats":[106],"frequency":[108],"as":[109],"exploitable":[110],"only":[111],"once":[112],"its":[113],"interval":[114],"separates":[115],"from":[116],"equilibrium":[118],"reference.":[119],"confirmed":[121],"define":[123],"conservative":[125],"model,":[127],"which":[128],"restricted-response":[130],"solve":[131],"turns":[132],"into":[133],"candidate":[134,146],"counter-strategies":[135],"over":[136],"grid":[138],"of":[139,200],"pin":[140],"levels.":[141],"Before":[142],"deployment,":[143],"each":[144],"complete":[145],"evaluated":[148],"full-tree":[151],"response.":[153],"resulting":[155],"compared":[158],"user-specified":[161],"budget":[162],"committed":[164],"atomically":[165],"strategy.":[168],"Because":[169],"this":[170],"check":[171],"performed":[173],"played":[176],"strategy,":[177],"quality":[179],"determines":[180],"exploitation":[182],"achieved":[183],"controls":[187],"reference-relative":[188],"expected":[189],"loss.":[190],"In":[191],"Leduc":[192],"hold'em,":[193],"CS-RNR":[194],"obtains":[195],"$6.2\\times$":[196],"steady-state":[198],"gain":[199],"money-verified":[202],"gate":[204],"keeping":[206],"deployed":[208],"within":[210],"budget.":[211,222],"A":[212],"trajectory":[213],"mixture":[214],"using":[215],"same":[217],"estimator":[218],"reaches":[219],"$13.6\\times$":[220],"Across":[223],"Leduc,":[224,229],"Liar's":[225],"Dice,":[226],"5-rank":[228],"all":[230],"$36{,}000$":[231],"hands":[233],"satisfy":[234],"reported":[236],"tolerance.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-01T00:00:00"}