{"id":"https://openalex.org/W7130405473","doi":"https://doi.org/10.48448/wwcy-aq50","title":"Reasoning Models Reason Well, Until They Don\u2019t","display_name":"Reasoning Models Reason Well, Until They Don\u2019t","publication_year":2025,"publication_date":"2025-12-01","ids":{"openalex":"https://openalex.org/W7130405473","doi":"https://doi.org/10.48448/wwcy-aq50"},"language":"en","primary_location":{"id":"doi:10.48448/wwcy-aq50","doi":"https://doi.org/10.48448/wwcy-aq50","is_oa":true,"landing_page_url":"https://doi.org/10.48448/wwcy-aq50","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"volume":null,"type":"other","is_traditional":false,"indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48448/wwcy-aq50","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126280765","display_name":"Association for Computational Linguistics 2025","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Association for Computational Linguistics 2025","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126346820","display_name":"Jimson Huang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huang, Jimson","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051031750","display_name":"R. Rameshkumar","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rameshkumar, Revanth","raw_affiliation_strings":["University of Washington"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062813195","display_name":"Abulhair Saparov","orcid":"https://orcid.org/0000-0002-0450-9125","observed_orcids":["https://orcid.org/0000-0002-0450-9125"]},"institutions":[{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saparov, Abulhair","raw_affiliation_strings":["Carnegie Mellon Univeristy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Carnegie Mellon Univeristy","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126298977","display_name":"Yunxin Sun","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun, Yunxin","raw_affiliation_strings":["Purdue University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Purdue University","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5126282416","display_name":"Fei Xia","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xia, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"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/T10028","display_name":"Topic Modeling","score":0.8877000212669373,"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/T10028","display_name":"Topic Modeling","score":0.8877000212669373,"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/T11010","display_name":"Logic, Reasoning, and Knowledge","score":0.04479999840259552,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.017500000074505806,"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/large-reasoning-models","display_name":"large reasoning models","score":0.9369999766349792},{"id":"https://openalex.org/keywords/catastrophic-failure","display_name":"catastrophic failure","score":0.48399999737739563},{"id":"https://openalex.org/keywords/reasoning-complexity","display_name":"reasoning complexity","score":0.5410000085830688},{"id":"https://openalex.org/keywords/generalization","display_name":"generalization","score":0.382999986410141},{"id":"https://openalex.org/keywords/graph-connectivity","display_name":"graph connectivity","score":0.7110000252723694},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.6930000185966492},{"id":"https://openalex.org/keywords/interaction-graphs","display_name":"interaction graphs","score":0.796999990940094},{"id":"https://openalex.org/keywords/self-verification","display_name":"self-verification","score":0.8550000190734863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5824000239372253},{"id":"https://openalex.org/C103057564","wikidata":"https://www.wikidata.org/wiki/Q4751139","display_name":"Analytic reasoning","level":3,"score":0.5206999778747559},{"id":"https://openalex.org/C65059942","wikidata":"https://www.wikidata.org/wiki/Q270105","display_name":"Argumentation theory","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.48420000076293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4794999957084656},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.44929999113082886},{"id":"https://openalex.org/C83725634","wikidata":"https://www.wikidata.org/wiki/Q7268699","display_name":"Qualitative reasoning","level":2,"score":0.3889999985694885},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.387800008058548},{"id":"https://openalex.org/C159032336","wikidata":"https://www.wikidata.org/wiki/Q2488768","display_name":"Non-monotonic logic","level":2,"score":0.32820001244544983},{"id":"https://openalex.org/C97364631","wikidata":"https://www.wikidata.org/wiki/Q484284","display_name":"Deductive reasoning","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.29179999232292175},{"id":"https://openalex.org/C89288958","wikidata":"https://www.wikidata.org/wiki/Q7301504","display_name":"Reasoning system","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C108710211","wikidata":"https://www.wikidata.org/wiki/Q11538","display_name":"Mathematical proof","level":2,"score":0.2824999988079071},{"id":"https://openalex.org/C195324797","wikidata":"https://www.wikidata.org/wiki/Q33742","display_name":"Natural language","level":2,"score":0.27790001034736633},{"id":"https://openalex.org/C43971567","wikidata":"https://www.wikidata.org/wiki/Q3142865","display_name":"Logical reasoning","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.26600000262260437},{"id":"https://openalex.org/C2779439875","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Natural language understanding","level":3,"score":0.260699987411499},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2563000023365021},{"id":"https://openalex.org/C192906763","wikidata":"https://www.wikidata.org/wiki/Q3376512","display_name":"Practical reason","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48448/wwcy-aq50","doi":"https://doi.org/10.48448/wwcy-aq50","is_oa":true,"landing_page_url":"https://doi.org/10.48448/wwcy-aq50","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"}],"best_oa_location":{"id":"doi:10.48448/wwcy-aq50","doi":"https://doi.org/10.48448/wwcy-aq50","is_oa":true,"landing_page_url":"https://doi.org/10.48448/wwcy-aq50","pdf_url":null,"source":{"id":"https://openalex.org/S7407053148","display_name":"Underline Science Inc.","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"Audiovisual"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417097899","https://openalex.org/W7154632117","https://openalex.org/W7163054852","https://openalex.org/W4416887915","https://openalex.org/W4414886088","https://openalex.org/W4415307670","https://openalex.org/W4414902777","https://openalex.org/W4416036399","https://openalex.org/W7128377138","https://openalex.org/W4414485088"],"abstract_inverted_index":{"Large":[0],"language":[1,135],"models":[2,37],"(LLMs)":[3],"have":[4,97],"shown":[5],"significant":[6],"progress":[7],"in":[8,72,219],"reasoning":[9,22,36,53,69,90],"tasks.":[10],"However,":[11,82],"recent":[12],"studies":[13],"show":[14,93],"that":[15,140,212],"transformers":[16],"and":[17,46,52,70,80,133,150,173],"LLMs":[18,39],"fail":[19],"catastrophically":[20],"once":[21],"problems":[23],"exceed":[24],"modest":[25],"complexity.":[26,99,121],"We":[27,100,122,138,154,176],"revisit":[28],"these":[29],"findings":[30],"through":[31],"the":[32,87,105,141,161,164,178,185,190,200,207,215,220],"lens":[33],"of":[34,67,89,119,143,163,166,180,203,217],"large":[35],"(LRMs)":[38],"fine-tuned":[40],"with":[41,60,111],"incentives":[42],"for":[43,115,209],"step\u2011by\u2011step":[44],"argumentation":[45],"self\u2011verification.":[47],"LRM":[48,158],"performance":[49,129,142],"on":[50,130],"graph":[51,131],"benchmarks":[54,95],"such":[55,75],"as":[56,76],"NLGraph":[57],"seem":[58],"extraordinary,":[59],"some":[61],"even":[62],"claiming":[63],"they":[64],"are":[65],"capable":[66],"generalized":[68],"innovation":[71],"reasoning-intensive":[73],"fields":[74],"mathematics,":[77],"physics,":[78],"medicine,":[79],"law.":[81],"by":[83],"more":[84],"carefully":[85],"scaling":[86],"complexity":[88,149,216],"problems,":[91],"we":[92],"existing":[94],"actually":[96],"limited":[98],"develop":[101],"a":[102,112],"new":[103,210],"dataset,":[104],"Deep":[106],"Reasoning":[107],"Dataset":[108],"(DeepRD),":[109],"along":[110],"generative":[113],"process":[114],"producing":[116],"unlimited":[117],"examples":[118,182,218],"scalable":[120],"use":[123],"this":[124],"dataset":[125],"to":[126,160],"evaluate":[127],"model":[128],"connectivity":[132],"natural":[134],"proof":[136,174],"planning.":[137],"find":[139,177],"LRMs":[144,204],"drop":[145],"abruptly":[146],"at":[147],"sufficient":[148],"do":[151],"not":[152],"generalize.":[153],"also":[155],"relate":[156],"our":[157],"results":[159],"distributions":[162],"complexities":[165],"large,":[167],"real-world":[168,181],"knowledge":[169],"graphs,":[170,172],"interaction":[171],"datasets.":[175],"majority":[179],"fall":[183],"inside":[184],"LRMs'":[186],"success":[187],"regime,":[188],"yet":[189],"long":[191],"tails":[192],"expose":[193],"substantial":[194],"failure":[195],"potential.":[196],"Our":[197],"analysis":[198],"highlights":[199],"near-term":[201],"utility":[202],"while":[205],"underscoring":[206],"need":[208],"methods":[211],"generalize":[213],"beyond":[214],"training":[221],"distribution.":[222]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-19T00:00:00"}