{"id":"https://openalex.org/W7163144654","doi":"https://doi.org/10.48550/arxiv.2606.02020","title":"Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning","display_name":"Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning","publication_year":2026,"publication_date":"2026-06-01","ids":{"openalex":"https://openalex.org/W7163144654","doi":"https://doi.org/10.48550/arxiv.2606.02020"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.02020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02020","pdf_url":null,"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":"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.02020","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137695777","display_name":"Ting Xu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Ting","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137688147","display_name":"Xu He","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"He, Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137710484","display_name":"Yupu Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Yupu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137676890","display_name":"Jiankai Sun","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Jiankai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137689140","display_name":"Dong Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Dong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111426224","display_name":"Wai Lam","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lam, Wai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hao, Jianye","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":false,"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/T11883","display_name":"Embodied and Extended Cognition","score":0.149399995803833,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T11883","display_name":"Embodied and Extended Cognition","score":0.149399995803833,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.12049999833106995,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.04439999908208847,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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/inference","display_name":"Inference","score":0.6547999978065491},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5859000086784363},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5361999869346619},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4894999861717224},{"id":"https://openalex.org/keywords/fiducial-inference","display_name":"Fiducial inference","score":0.41760000586509705},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.39989998936653137},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.3889000117778778},{"id":"https://openalex.org/keywords/confidence-interval","display_name":"Confidence interval","score":0.3790000081062317}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6547999978065491},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6502000093460083},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5859000086784363},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5361999869346619},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4894999861717224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4332999885082245},{"id":"https://openalex.org/C95167961","wikidata":"https://www.wikidata.org/wiki/Q4483495","display_name":"Fiducial inference","level":5,"score":0.41760000586509705},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.39989998936653137},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3944999873638153},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.3889000117778778},{"id":"https://openalex.org/C44249647","wikidata":"https://www.wikidata.org/wiki/Q208498","display_name":"Confidence interval","level":2,"score":0.3790000081062317},{"id":"https://openalex.org/C13662513","wikidata":"https://www.wikidata.org/wiki/Q5160087","display_name":"Confidence distribution","level":3,"score":0.37450000643730164},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35530000925064087},{"id":"https://openalex.org/C178518018","wikidata":"https://www.wikidata.org/wiki/Q1024555","display_name":"CUSUM","level":2,"score":0.3456000089645386},{"id":"https://openalex.org/C162376815","wikidata":"https://www.wikidata.org/wiki/Q2158281","display_name":"Frequentist inference","level":4,"score":0.3449000120162964},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.3443000018596649},{"id":"https://openalex.org/C171752962","wikidata":"https://www.wikidata.org/wiki/Q255166","display_name":"Kullback\u2013Leibler divergence","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.34060001373291016},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.289900004863739},{"id":"https://openalex.org/C63002673","wikidata":"https://www.wikidata.org/wiki/Q2260590","display_name":"Scoring rule","level":2,"score":0.2897000014781952},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.27129998803138733},{"id":"https://openalex.org/C134261354","wikidata":"https://www.wikidata.org/wiki/Q938438","display_name":"Statistical inference","level":2,"score":0.2671000063419342},{"id":"https://openalex.org/C102366305","wikidata":"https://www.wikidata.org/wiki/Q1097688","display_name":"Nonparametric statistics","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C3770464","wikidata":"https://www.wikidata.org/wiki/Q775963","display_name":"Smoothing","level":2,"score":0.25130000710487366}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.02020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02020","pdf_url":null,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.02020","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.02020","pdf_url":null,"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":"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"paper":[1],"investigates":[2],"the":[3,31,44,64,94,118,130],"entropy":[4],"dynamics":[5],"of":[6,18,26],"Chain-of-Thought":[7],"(CoT)":[8],"and":[9,50,52,72,81,90,170,174],"uncovers":[10],"a":[11,23,112,135,142,154],"consistent":[12],"two-phase":[13],"structure:":[14],"an":[15],"Uncertainty":[16],"Region":[17,25,33,96,109],"exploration":[19],"transitioning":[20],"sharply":[21],"to":[22,83,98,120,125],"Confidence":[24,32,95,108],"convergence.":[27],"We":[28],"demonstrate":[29],"that":[30],"possesses":[34],"two":[35],"critical":[36],"properties:":[37],"1)":[38,76],"High":[39,54],"Reliability":[40],"--":[41,56],"answers":[42],"in":[43,176],"confidence":[45],"region":[46],"become":[47],"highly":[48],"accurate":[49],"stable,":[51],"2)":[53],"Redundancy":[55],"models":[57],"generate":[58],"unnecessary":[59],"tokens":[60],"long":[61],"after":[62],"reaching":[63],"correct":[65],"answer.":[66],"These":[67],"properties":[68],"unlock":[69],"more":[70],"efficient":[71],"reliable":[73],"inference":[74,147],"strategies:":[75],"Early":[77],"Exit":[78],"leverages":[79],"reliability":[80],"redundancy":[82],"terminate":[84],"computation":[85],"safely":[86],"when":[87],"returns":[88],"diminish,":[89],"2)Test-Time":[91],"Scaling":[92],"uses":[93],"signal":[97],"prioritize":[99],"converged":[100],"trajectories.":[101],"To":[102],"operationalize":[103],"these":[104],"insights,":[105],"we":[106,140],"formulate":[107],"detection":[110,115],"as":[111],"sequential":[113],"change-point":[114,123,138],"problem,":[116],"being":[117],"first":[119],"apply":[121],"classical":[122],"methods":[124],"monitor":[126],"CoT":[127],"reasoning.":[128],"Using":[129],"Cumulative":[131],"Sum":[132],"(CUSUM)":[133],"algorithm,":[134],"statistically":[136],"optimal":[137],"detector,":[139],"develop":[141],"training-free":[143],"framework":[144],"for":[145,157],"real-time":[146],"control.":[148],"Experiments":[149],"show":[150],"our":[151],"approach":[152],"establishes":[153],"superior":[155],"Pareto-frontier":[156],"early":[158],"exit.":[159],"CUSUM":[160],"achieves":[161],"63.06%":[162],"accuracy":[163,177],"with":[164],"11.1%":[165],"token":[166],"reduction,":[167],"outperforming":[168],"DEER":[169],"Dynasor":[171],"by":[172],"3.28%":[173],"4.36%":[175],"respectively.":[178],"For":[179],"test-time":[180],"scaling,":[181],"CUSUM-weighted":[182],"voting":[183],"consistently":[184],"outperforms":[185],"self-consistency.":[186]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-03T00:00:00"}