{"id":"https://openalex.org/W7204246982","doi":"https://doi.org/10.48550/arxiv.2608.24691","title":"Confident at the moment of action: belief miscalibration in LLM play under hidden information","display_name":"Confident at the moment of action: belief miscalibration in LLM play under hidden information","publication_year":2026,"publication_date":"2026-08-25","ids":{"openalex":"https://openalex.org/W7204246982","doi":"https://doi.org/10.48550/arxiv.2608.24691"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.24691","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24691","pdf_url":"https://arxiv.org/pdf/2608.24691","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/2608.24691","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5148289701","display_name":"Bhushan Kashinath Joshi","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Joshi, Bhushan Kashinath","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5148289701"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"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":0.24719999730587006,"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":0.24719999730587006,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.13979999721050262,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.08309999853372574,"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/confidence-calibration","display_name":"confidence calibration","score":0.671999990940094},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9120000004768372},{"id":"https://openalex.org/keywords/hidden-information","display_name":"hidden information","score":0.7059999704360962},{"id":"https://openalex.org/keywords/chess-variants","display_name":"chess variants","score":0.7829999923706055}],"concepts":[{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.6751000285148621},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.6316999793052673},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5909000039100647},{"id":"https://openalex.org/C179254644","wikidata":"https://www.wikidata.org/wiki/Q13222844","display_name":"Moment (physics)","level":2,"score":0.5767999887466431},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5476999878883362},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.5214999914169312},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47530001401901245},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4729999899864197},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.4684999883174896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4253000020980835},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.3930000066757202},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.3862000107765198},{"id":"https://openalex.org/C2776157432","wikidata":"https://www.wikidata.org/wiki/Q1375683","display_name":"Normality","level":2,"score":0.3646000027656555},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.3625999987125397},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.35670000314712524},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.35089999437332153},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.3337000012397766},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.3336000144481659},{"id":"https://openalex.org/C25343380","wikidata":"https://www.wikidata.org/wiki/Q277521","display_name":"Relation (database)","level":2,"score":0.3100000023841858},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.2906999886035919},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.27790001034736633},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.27720001339912415},{"id":"https://openalex.org/C128913409","wikidata":"https://www.wikidata.org/wiki/Q3566063","display_name":"Belief revision","level":2,"score":0.26840001344680786},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2554999887943268},{"id":"https://openalex.org/C97399411","wikidata":"https://www.wikidata.org/wiki/Q825367","display_name":"Coin flipping","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C177142836","wikidata":"https://www.wikidata.org/wiki/Q44455","display_name":"Game theory","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.2513999938964844},{"id":"https://openalex.org/C129848803","wikidata":"https://www.wikidata.org/wiki/Q2564360","display_name":"Sample size determination","level":2,"score":0.25029999017715454},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.24691","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24691","pdf_url":"https://arxiv.org/pdf/2608.24691","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.2608.24691","doi":"https://doi.org/10.48550/arxiv.2608.24691","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.24691","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:2608.24691","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.24691","pdf_url":"https://arxiv.org/pdf/2608.24691","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/W7204246982.pdf","grobid_xml":"https://content.openalex.org/works/W7204246982.grobid-xml"},"referenced_works_count":12,"referenced_works":["https://openalex.org/W4285429195","https://openalex.org/W4403580391","https://openalex.org/W4415338101","https://openalex.org/W4416361850","https://openalex.org/W4416763768","https://openalex.org/W4417289967","https://openalex.org/W7151296013","https://openalex.org/W7160980601","https://openalex.org/W7162674038","https://openalex.org/W7166797992","https://openalex.org/W7168270908","https://openalex.org/W7170385212"],"related_works":["https://openalex.org/W4416361850","https://openalex.org/W7221061483","https://openalex.org/W7221776908","https://openalex.org/W7168251463","https://openalex.org/W4415035550","https://openalex.org/W7220991868","https://openalex.org/W7168095457","https://openalex.org/W7160043529","https://openalex.org/W7212139499","https://openalex.org/W7170149988"],"abstract_inverted_index":{"Agentic":[0],"systems":[1],"increasingly":[2],"gate":[3],"actions":[4],"on":[5,212],"a":[6,25,145,162,166,172,184,189],"model's":[7],"own":[8],"stated":[9,43,80],"confidence,":[10],"which":[11,236],"assumes":[12],"confidence":[13,81],"tracks":[14],"correctness":[15],"at":[16,78,135,165],"the":[17,47,58,70,85,110,115,153,177,209,217,230],"moment":[18],"of":[19,93,107],"acting.":[20],"We":[21],"test":[22],"this":[23,136,225],"in":[24,91,103,109,114,120],"hidden-information":[26],"chess":[27],"variant":[28],"where":[29,40],"royal":[30,50],"status":[31],"can":[32,202,227],"be":[33],"secretly,":[34],"repeatedly":[35],"relocated":[36],"between":[37],"pieces,":[38],"and":[39],"an":[41],"agent's":[42],"probability":[44],"distribution":[45],"over":[46],"opponent's":[48],"hidden":[49,86],"piece":[51],"--":[52,62,148,195,201],"elicited":[53],"every":[54,213],"turn,":[55],"separately":[56],"from":[57,205],"move":[59],"it":[60,108],"chooses":[61],"is":[63,99,237],"scored":[64],"against":[65],"ground":[66],"truth":[67],"recoverable":[68],"after":[69],"game.":[71],"Across":[72],"two":[73],"independent":[74],"batches,":[75],"captures":[76],"made":[77],"high":[79],"($\\geq":[82],"0.5$)":[83],"about":[84],"piece's":[87],"location":[88],"were":[89],"correct":[90],"1":[92],"62":[94],"cases.":[95],"The":[96,117],"calibration":[97],"deficit":[98],"concentrated":[100],"almost":[101],"entirely":[102,204],"these":[104],"events:":[105],"99.3%":[106],"original":[111],"batch,":[112],"98.7%":[113],"replication.":[116],"same":[118],"pattern,":[119],"weaker":[121],"form,":[122],"orders":[123],"consistently":[124],"(point":[125],"estimates":[126],"only;":[127],"most":[128],"pairwise":[129],"gaps":[130],"are":[131],"not":[132,155,242],"statistically":[133],"distinguishable":[134],"sample":[137],"size)":[138],"across":[139],"four":[140],"further":[141],"model":[142,223],"configurations":[143],"spanning":[144],"second":[146],"provider":[147],"reported":[149],"as":[150,156,181,183],"scope":[151],"for":[152],"finding,":[154],"evidence":[157],"that":[158],"capability":[159],"predicts":[160],"calibration:":[161],"same-model":[163],"comparison":[164],"fixed":[167],"external":[168],"leaderboard":[169],"score":[170],"shows":[171],"deliberation-budget":[173],"change":[174],"alone":[175],"moves":[176],"metric":[178],"by":[179],"nearly":[180],"much":[182],"large":[185],"cross-model":[186],"gap.":[187],"In":[188],"separate":[190],"seat,":[191],"conventional":[192,214],"evaluation":[193,240],"axes":[194],"legality,":[196],"cost,":[197],"latency,":[198],"completion":[199],"rate":[200],"dissociate":[203],"belief":[206,219,233],"quality,":[207],"with":[208],"configuration":[210],"winning":[211],"axis":[215],"producing":[216],"worst":[218],"quality":[220],"tested.":[221],"A":[222],"exhibiting":[224],"pattern":[226],"still":[228],"win":[229],"game":[231],"its":[232],"was":[234],"about,":[235],"why":[238],"outcome-only":[239],"would":[241],"detect":[243],"it.":[244]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-27T00:00:00"}