{"id":"https://openalex.org/W4412886683","doi":"https://doi.org/10.18653/v1/2025.acl-long.232","title":"Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?","display_name":"Revisiting the Test-Time Scaling of o1-like Models: Do they Truly Possess Test-Time Scaling Capabilities?","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412886683","doi":"https://doi.org/10.18653/v1/2025.acl-long.232"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.232","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.232","pdf_url":"https://aclanthology.org/2025.acl-long.232.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2025.acl-long.232.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075168326","display_name":"Zhiyuan Zeng","orcid":"https://orcid.org/0000-0002-3979-3322"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhiyuan Zeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004651932","display_name":"Qinyuan Cheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qinyuan Cheng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083955516","display_name":"Zhangyue Yin","orcid":"https://orcid.org/0009-0008-0620-8271"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhangyue Yin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102710198","display_name":"Yunhua Zhou","orcid":"https://orcid.org/0000-0002-6907-7167"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yunhua Zhou","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5044665993","display_name":"Xipeng Qiu","orcid":"https://orcid.org/0000-0001-7163-5247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xipeng Qiu","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":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4651","last_page":"4665"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.6579999923706055,"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"}},"topics":[{"id":"https://openalex.org/T12205","display_name":"Time Series Analysis and Forecasting","score":0.6579999923706055,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.6464999914169312,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"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/T10028","display_name":"Topic Modeling","score":0.6306999921798706,"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/scaling","display_name":"Scaling","score":0.6981449723243713},{"id":"https://openalex.org/keywords/test","display_name":"Test (biology)","score":0.6600840091705322},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6082866191864014},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18682420253753662}],"concepts":[{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6981449723243713},{"id":"https://openalex.org/C2777267654","wikidata":"https://www.wikidata.org/wiki/Q3519023","display_name":"Test (biology)","level":2,"score":0.6600840091705322},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6082866191864014},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18682420253753662},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.232","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.232","pdf_url":"https://aclanthology.org/2025.acl-long.232.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2025.acl-long.232","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.232","pdf_url":"https://aclanthology.org/2025.acl-long.232.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412886683.pdf","grobid_xml":"https://content.openalex.org/works/W4412886683.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"advent":[1],"of":[2,51],"test-time":[3,41,139],"scaling":[4,20,42,101,111,130],"in":[5,60],"large":[6],"language":[7],"models":[8,38,54],"(LLMs),":[9],"exemplified":[10],"by":[11,19],"Ope-nAI's":[12],"o1":[13],"series,":[14],"has":[15],"advanced":[16],"reasoning":[17],"capabilities":[18,43,84],"computational":[21],"resource":[22],"allocation":[23],"during":[24],"inference.While":[25],"successors":[26],"like":[27],"QwQ,":[28,104],"Deepseek-R1":[29],"(R1)":[30],"and":[31,99,106,115],"LIMO":[32],"replicate":[33],"these":[34,37,52,118],"advancements,":[35],"whether":[36],"truly":[39],"possess":[40],"remains":[44],"underexplored.This":[45],"study":[46],"found":[47],"that":[48,109,127],"longer":[49],"CoTs":[50,86],"o1-like":[53],"do":[55],"not":[56],"consistently":[57],"enhance":[58],"accuracy;":[59],"fact,":[61],"correct":[62],"solutions":[63],"are":[64],"often":[65,91],"shorter":[66],"than":[67],"incorrect":[68],"ones":[69],"for":[70],"the":[71],"same":[72],"questions.Further":[73],"investigation":[74],"shows":[75],"this":[76],"phenomenon":[77],"is":[78],"closely":[79],"related":[80],"to":[81,93,142],"models'":[82,138],"self-revision":[83],"-longer":[85],"contain":[87],"more":[88],"self-revisions,":[89],"which":[90],"lead":[92],"performance":[94],"degradation.We":[95],"then":[96],"compare":[97],"sequential":[98],"parallel":[100,110,129],"strategies":[102,131],"on":[103,117],"R1":[105],"LIMO,":[107],"finding":[108],"achieves":[112],"better":[113],"coverage":[114],"scalability.Based":[116],"insights,":[119],"we":[120],"propose":[121],"Shortest":[122],"Majority":[123],"Vote,":[124],"a":[125],"method":[126],"combines":[128],"with":[132],"CoT":[133],"length":[134],"characteristics,":[135],"significantly":[136],"improving":[137],"scalability":[140],"compared":[141],"conventional":[143],"majority":[144],"voting":[145],"approaches.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}