{"id":"https://openalex.org/W7128404479","doi":"https://doi.org/10.48550/arxiv.2602.06948","title":"Agentic Uncertainty Reveals Agentic Overconfidence","display_name":"Agentic Uncertainty Reveals Agentic Overconfidence","publication_year":2026,"publication_date":"2026-02-06","ids":{"openalex":"https://openalex.org/W7128404479","doi":"https://doi.org/10.48550/arxiv.2602.06948"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.06948","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.06948","pdf_url":"https://arxiv.org/pdf/2602.06948","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":"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/2602.06948","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5055937590","display_name":"Jean Kaddour","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Kaddour, Jean","raw_affiliation_strings":["SevnAI","University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SevnAI","institution_ids":[]},{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125422344","display_name":"Srijan Patel","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Patel, Srijan","raw_affiliation_strings":["SevnAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"SevnAI","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125378121","display_name":"Gb\u00e8tondji Dovonon","orcid":"https://orcid.org/0009-0001-5249-1089","observed_orcids":["https://orcid.org/0009-0001-5249-1089"]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dovonon, Gb\u00e8tondji","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125400590","display_name":"Leo Richter","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richter, Leo","raw_affiliation_strings":["University College London"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University College London","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019106673","display_name":"Pasquale Minervini","orcid":"https://orcid.org/0000-0002-8442-602X","observed_orcids":["https://orcid.org/0000-0002-8442-602X"]},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Minervini, Pasquale","raw_affiliation_strings":["University of Edinburgh"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108523545","display_name":"Matt J. Kusner","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I45683168","display_name":"Polytechnique Montr\u00e9al","ror":"https://ror.org/05f8d4e86","country_code":"CA","type":"education","lineage":["https://openalex.org/I45683168"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Kusner, Matt J.","raw_affiliation_strings":["Mila -Qu\u00e9bec AI Institute","Polytechnique Montr\u00e9al "],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mila -Qu\u00e9bec AI Institute","institution_ids":["https://openalex.org/I4210164802"]},{"raw_affiliation_string":"Polytechnique Montr\u00e9al ","institution_ids":["https://openalex.org/I45683168"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":9,"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":0.3212999999523163,"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":0.3212999999523163,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.09179999679327011,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.051100000739097595,"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/success-probability-estimation","display_name":"success probability estimation","score":0.7559999823570251},{"id":"https://openalex.org/keywords/ai-agents","display_name":"AI agents","score":0.6650000214576721},{"id":"https://openalex.org/keywords/calibration","display_name":"calibration","score":0.6520000100135803},{"id":"https://openalex.org/keywords/adversarial-prompting","display_name":"adversarial prompting","score":0.7630000114440918}],"concepts":[{"id":"https://openalex.org/C51110983","wikidata":"https://www.wikidata.org/wiki/Q16503490","display_name":"Overconfidence effect","level":2,"score":0.8626999855041504},{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.6639000177383423},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5383999943733215},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.5235999822616577},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.45559999346733093},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.4551999866962433},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4156999886035919},{"id":"https://openalex.org/C10347200","wikidata":"https://www.wikidata.org/wiki/Q1960297","display_name":"Hindsight bias","level":2,"score":0.40720000863075256},{"id":"https://openalex.org/C2776325391","wikidata":"https://www.wikidata.org/wiki/Q6917865","display_name":"Motivated reasoning","level":3,"score":0.39500001072883606},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.37860000133514404},{"id":"https://openalex.org/C134121241","wikidata":"https://www.wikidata.org/wiki/Q899301","display_name":"Yield (engineering)","level":2,"score":0.3488999903202057},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3100999891757965},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.30720001459121704},{"id":"https://openalex.org/C98184364","wikidata":"https://www.wikidata.org/wiki/Q1780131","display_name":"Argument (complex analysis)","level":2,"score":0.3068000078201294},{"id":"https://openalex.org/C108170787","wikidata":"https://www.wikidata.org/wiki/Q3951828","display_name":"Agency (philosophy)","level":2,"score":0.29829999804496765},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2784000039100647},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.2775000035762787},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.27059999108314514},{"id":"https://openalex.org/C28901747","wikidata":"https://www.wikidata.org/wiki/Q177571","display_name":"Decision theory","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C2777340749","wikidata":"https://www.wikidata.org/wiki/Q6684955","display_name":"Lottery","level":2,"score":0.257999986410141}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.06948","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.06948","pdf_url":"https://arxiv.org/pdf/2602.06948","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2602.06948","doi":"https://doi.org/10.48550/arxiv.2602.06948","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.06948","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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.06948","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.06948","pdf_url":"https://arxiv.org/pdf/2602.06948","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":"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/W7128404479.pdf","grobid_xml":"https://content.openalex.org/works/W7128404479.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W2798877128","https://openalex.org/W3210904070","https://openalex.org/W4285429195","https://openalex.org/W4308615640","https://openalex.org/W4321594373","https://openalex.org/W4379089709","https://openalex.org/W4385327683","https://openalex.org/W4387355948","https://openalex.org/W4391800466","https://openalex.org/W4391833261","https://openalex.org/W4399116108","https://openalex.org/W4405253355","https://openalex.org/W4414427575","https://openalex.org/W4414973934","https://openalex.org/W4415030372","https://openalex.org/W4415089340","https://openalex.org/W4415160738","https://openalex.org/W4415252687","https://openalex.org/W4415797148","https://openalex.org/W4416176618","https://openalex.org/W4417163898","https://openalex.org/W7106274751","https://openalex.org/W7117966065","https://openalex.org/W7125552633"],"related_works":["https://openalex.org/W7214545164","https://openalex.org/W7212139499","https://openalex.org/W7214128477","https://openalex.org/W7221776908","https://openalex.org/W7220649427","https://openalex.org/W7125502694","https://openalex.org/W7204898988","https://openalex.org/W7117966065","https://openalex.org/W7212081179","https://openalex.org/W7166874648"],"abstract_inverted_index":{"Can":[0],"AI":[1],"agents":[2,32],"predict":[3,40],"whether":[4],"they":[5],"will":[6],"succeed":[7,34],"at":[8],"a":[9],"task?":[10],"We":[11],"study":[12],"agentic":[13,29],"uncertainty":[14],"by":[15],"eliciting":[16],"success":[17],"probability":[18],"estimates":[19],"before,":[20],"during,":[21],"and":[22],"after":[23],"task":[24],"execution.":[25],"All":[26],"results":[27],"exhibit":[28],"overconfidence:":[30],"some":[31],"that":[33],"only":[35],"22%":[36],"of":[37],"the":[38,72],"time":[39],"77%":[41],"success.":[42],"Counterintuitively,":[43],"pre-execution":[44],"assessment":[45,68],"with":[46],"strictly":[47],"less":[48],"information":[49],"tends":[50],"to":[51],"yield":[52],"better":[53],"discrimination":[54],"than":[55],"standard":[56],"post-execution":[57],"review,":[58],"though":[59],"differences":[60],"are":[61],"not":[62],"always":[63],"significant.":[64],"Adversarial":[65],"prompting":[66],"reframing":[67],"as":[69],"bug-finding":[70],"achieves":[71],"best":[73],"calibration.":[74]},"counts_by_year":[{"year":2026,"cited_by_count":9}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-02-10T00:00:00"}