{"id":"https://openalex.org/W4412944736","doi":"https://doi.org/10.18653/v1/2025.acl-long.1145","title":"Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models","display_name":"Marco-o1 v2: Towards Widening The Distillation Bottleneck for Reasoning Models","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4412944736","doi":"https://doi.org/10.18653/v1/2025.acl-long.1145"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2025.acl-long.1145","doi":"https://doi.org/10.18653/v1/2025.acl-long.1145","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1145","pdf_url":"https://aclanthology.org/2025.acl-long.1145.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"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"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2025.acl-long.1145.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Huifeng Yin","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huifeng Yin","raw_affiliation_strings":["Alibaba International Digital Commerce","Tsinghua University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Tsinghua University","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085767277","display_name":"Yu Qiang Zhao","orcid":"https://orcid.org/0000-0003-1081-3841","observed_orcids":["https://orcid.org/0000-0003-1081-3841"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhao","raw_affiliation_strings":["Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022151811","display_name":"Minghao Wu","orcid":"https://orcid.org/0000-0001-7185-0318","observed_orcids":["https://orcid.org/0000-0001-7185-0318","https://orcid.org/0009-0003-7208-3992"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]},{"id":"https://openalex.org/I56590836","display_name":"Monash University","ror":"https://ror.org/02bfwt286","country_code":"AU","type":"education","lineage":["https://openalex.org/I56590836"]}],"countries":["AU","CN"],"is_corresponding":false,"raw_author_name":"Minghao Wu","raw_affiliation_strings":["Alibaba International Digital Commerce","Monash University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]},{"raw_affiliation_string":"Monash University","institution_ids":["https://openalex.org/I56590836"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035601720","display_name":"Xuanfan Ni","orcid":"https://orcid.org/0009-0006-9785-2956","observed_orcids":["https://orcid.org/0009-0006-9785-2956"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuanfan Ni","raw_affiliation_strings":["Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo Zeng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Zeng","raw_affiliation_strings":["Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119204333","display_name":"Huaiyu.wh Huaiyu.wh","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huaiyu.wh Huaiyu.wh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Tianqi Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tianqi Shi","raw_affiliation_strings":["Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Liangying Shao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liangying Shao","raw_affiliation_strings":["Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chenyang Lyu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Lyu","raw_affiliation_strings":["Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088191810","display_name":"Longyue Wang","orcid":"https://orcid.org/0000-0002-9062-6183","observed_orcids":["https://orcid.org/0000-0002-9062-6183","https://orcid.org/0009-0009-4675-0417"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Longyue Wang","raw_affiliation_strings":["Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085736941","display_name":"Weihua Luo","orcid":"https://orcid.org/0000-0002-5002-6933","observed_orcids":["https://orcid.org/0000-0002-5002-6933"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weihua Luo","raw_affiliation_strings":["Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062350665","display_name":"Kaifu Zhang","orcid":"https://orcid.org/0000-0003-2756-2196","observed_orcids":["https://orcid.org/0000-0003-2756-2196"]},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaifu Zhang","raw_affiliation_strings":["Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9496,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71840171,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"23506","last_page":"23516"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.3571999967098236,"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":0.3571999967098236,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.3158999979496002,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.10679999738931656,"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/knowledge-distillation","display_name":"knowledge distillation","score":0.8830000162124634},{"id":"https://openalex.org/keywords/reasoning-models","display_name":"reasoning models","score":0.8629999756813049},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.7379999756813049},{"id":"https://openalex.org/keywords/model-compression","display_name":"model compression","score":0.5099999904632568}],"concepts":[{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.9054160118103027},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.587577760219574},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5592230558395386},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.1380288004875183},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.09743621945381165},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.08496454358100891}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.18653/v1/2025.acl-long.1145","doi":"https://doi.org/10.18653/v1/2025.acl-long.1145","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1145","pdf_url":"https://aclanthology.org/2025.acl-long.1145.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"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"},{"id":"pmh:oai:arXiv.org:2503.01461","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.01461","pdf_url":"https://arxiv.org/pdf/2503.01461","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.2503.01461","doi":"https://doi.org/10.48550/arxiv.2503.01461","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.01461","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":"doi:10.18653/v1/2025.acl-long.1145","doi":"https://doi.org/10.18653/v1/2025.acl-long.1145","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2025.acl-long.1145","pdf_url":"https://aclanthology.org/2025.acl-long.1145.pdf","source":{"id":"https://openalex.org/S4393915740","display_name":"Proceedings of the conference - Association for Computational Linguistics. Meeting","issn_l":"0736-587X","issn":["0736-587X"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412944736.pdf","grobid_xml":"https://content.openalex.org/works/W4412944736.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4415137708","https://openalex.org/W7204933937","https://openalex.org/W4385571831","https://openalex.org/W4415332738","https://openalex.org/W4415132736","https://openalex.org/W7166843076","https://openalex.org/W7083815555","https://openalex.org/W4385571219","https://openalex.org/W4412944484","https://openalex.org/W7166802716"],"abstract_inverted_index":{"Large":[0],"Reasoning":[1],"Models":[2],"(LRMs)":[3],"such":[4,126],"as":[5,127],"Ope-nAI":[6],"o1":[7],"and":[8,19,60,73,108,115,133],"DeepSeek-R1":[9],"have":[10],"shown":[11],"remarkable":[12],"reasoning":[13,37,143],"capabilities":[14],"by":[15],"scaling":[16],"testtime":[17],"compute":[18],"generating":[20],"long":[21,51],"Chain-of-Thought":[22],"(CoT).Distillation":[23],"post-training":[24],"on":[25,117,123],"LRMs-generated":[26],"data":[27,53,86],"is":[28,162],"a":[29,44,97],"straightforward":[30],"yet":[31],"effective":[32],"method":[33],"to":[34,62,112,149],"enhance":[35,113],"the":[36,63,118,142,155],"abilities":[38],"of":[39,65,99,145],"smaller":[40],"models,":[41],"but":[42],"faces":[43],"critical":[45],"bottleneck:":[46],"we":[47,81],"found":[48],"that":[49],"distilled":[50,146,151],"CoT":[52,85],"poses":[54],"learning":[55],"difficulty":[56],"for":[57],"small":[58],"models":[59,147,152],"leads":[61],"inheritance":[64],"biases":[66],"(i.e.over-thinking)":[67],"when":[68],"using":[69],"Supervised":[70],"Fine-tuning":[71],"(SFT)":[72],"Reinforcement":[74],"Learning":[75],"(RL)":[76],"methods.To":[77],"alleviate":[78],"this":[79],"bottleneck,":[80],"propose":[82],"constructing":[83],"tree-based":[84],"from":[87],"scratch":[88],"via":[89,153],"Monte":[90],"Carlo":[91],"Tree":[92],"Search":[93],"(MCTS).We":[94],"then":[95],"exploit":[96],"set":[98],"CoTaware":[100],"approaches,":[101],"including":[102],"Thoughts":[103],"Length":[104],"Balance,":[105],"Fine-grained":[106],"DPO,":[107],"Joint":[109],"Posttraining":[110],"Objective,":[111],"SFT":[114],"RL":[116],"construted":[119],"data.We":[120],"conduct":[121],"evaluation":[122],"various":[124],"benchmarks":[125],"math":[128],"(GSM8K,":[129],"MATH,":[130],"AIME).instruction-following":[131],"(Multi-IF)":[132],"planning":[134],"(Blocksworld),":[135],"results":[136],"demonstrate":[137],"our":[138],"approaches":[139],"substantially":[140],"improve":[141],"performance":[144],"compared":[148],"standard":[150],"reducing":[154],"hallucinations":[156],"in":[157],"long-time":[158],"thinking.The":[159],"project":[160],"homepage":[161],"https://github.com/":[163],"AIDC-AI/Marco-o1.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2025-10-10T00:00:00"}
