{"id":"https://openalex.org/W4405355299","doi":"https://doi.org/10.48550/arxiv.2412.09413","title":"Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems","display_name":"Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems","publication_year":2024,"publication_date":"2024-12-12","ids":{"openalex":"https://openalex.org/W4405355299","doi":"https://doi.org/10.48550/arxiv.2412.09413"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2412.09413","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.09413","pdf_url":"https://arxiv.org/pdf/2412.09413","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2412.09413","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059541770","display_name":"Yingqian Min","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Min, Yingqian","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325082","display_name":"Zhipeng Chen","orcid":"https://orcid.org/0000-0002-5890-3072","observed_orcids":["https://orcid.org/0000-0002-5890-3072"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Zhipeng","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049018103","display_name":"Jinhao Jiang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiang, Jinhao","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chen, Jie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen, Jie","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021133065","display_name":"Jia Deng","orcid":"https://orcid.org/0000-0001-7323-6100","observed_orcids":["https://orcid.org/0000-0001-7323-6100"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deng, Jia","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hu, Yiwen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu, Yiwen","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108953428","display_name":"Yiru Tang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tang, Yiru","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695120","display_name":"Jiapeng Wang","orcid":"https://orcid.org/0000-0003-1498-0305","observed_orcids":["https://orcid.org/0000-0003-1498-0305"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Jiapeng","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101143771","display_name":"Xiaoxue Cheng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng, Xiaoxue","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Song, Huatong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song, Huatong","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037145565","display_name":"Wayne Xin Zhao","orcid":"https://orcid.org/0000-0002-8333-6196","observed_orcids":["https://orcid.org/0000-0002-8333-6196"]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao, Wayne Xin","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100423656","display_name":"Zheng Liu","orcid":"https://orcid.org/0000-0001-7765-8466","observed_orcids":["https://orcid.org/0000-0001-7765-8466","https://orcid.org/0009-0006-1277-0493","https://orcid.org/0000-0003-3437-2630"]},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Zheng","raw_affiliation_strings":["BAAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BAAI","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110942112","display_name":"Zhongyuan Wang","orcid":"https://orcid.org/0009-0005-7313-0855","observed_orcids":["https://orcid.org/0009-0005-7313-0855"]},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wang, Zhongyuan","raw_affiliation_strings":["BAAI"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"BAAI","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063092268","display_name":"Ji-Rong Wen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wen, Ji-Rong","raw_affiliation_strings":["Gaoling School of Artificial Intelligence , Renmin University of China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence , Renmin University of China","institution_ids":["https://openalex.org/I78988378"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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":0.6133000254631042,"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":0.6133000254631042,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.12039999663829803,"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":0.06880000233650208,"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/o1","display_name":"O1","score":0.6209999918937683},{"id":"https://openalex.org/keywords/fine-tuning","display_name":"fine-tuning","score":0.6779999732971191},{"id":"https://openalex.org/keywords/personal-development","display_name":"human development","score":0.8069999814033508},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.4390000104904175},{"id":"https://openalex.org/keywords/reasoning-benchmarks","display_name":"reasoning benchmarks","score":0.3070000112056732},{"id":"https://openalex.org/keywords/open-source-implementation","display_name":"open-source implementation","score":0.40400001406669617}],"concepts":[{"id":"https://openalex.org/C59659247","wikidata":"https://www.wikidata.org/wiki/Q11990","display_name":"Reproduction","level":2,"score":0.637580156326294},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.334617018699646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.32167014479637146},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.19731634855270386},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1491023302078247}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2412.09413","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.09413","pdf_url":"https://arxiv.org/pdf/2412.09413","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.2412.09413","doi":"https://doi.org/10.48550/arxiv.2412.09413","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2412.09413","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:2412.09413","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2412.09413","pdf_url":"https://arxiv.org/pdf/2412.09413","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/W4405355299.pdf","grobid_xml":"https://content.openalex.org/works/W4405355299.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7081972478","https://openalex.org/W4416095101","https://openalex.org/W4416113814","https://openalex.org/W4406735009","https://openalex.org/W4406093553","https://openalex.org/W4414858785","https://openalex.org/W4415132780","https://openalex.org/W4415344873","https://openalex.org/W4407308614","https://openalex.org/W4403571786"],"abstract_inverted_index":{"Recently,":[0],"slow-thinking":[1,135],"reasoning":[2,14,76,92,113,128,202],"systems,":[3],"such":[4],"as":[5,103,105],"o1,":[6],"have":[7],"demonstrated":[8],"remarkable":[9],"capabilities":[10],"in":[11,20,153],"solving":[12],"complex":[13],"tasks.":[15],"These":[16,40],"systems":[17,41,203],"typically":[18],"engage":[19],"an":[21,58,96],"extended":[22],"thinking":[23],"process":[24],"before":[25],"responding":[26],"to":[27,32,68,110,125,132,142,160,200],"a":[28,86,134],"query,":[29],"allowing":[30],"them":[31],"generate":[33],"more":[34,155],"thorough,":[35],"accurate,":[36],"and":[37,45,99],"well-reasoned":[38],"solutions.":[39],"are":[42],"primarily":[43],"developed":[44],"maintained":[46],"by":[47,146,168],"industry,":[48],"with":[49],"their":[50],"core":[51],"techniques":[52],"not":[53],"publicly":[54],"disclosed.":[55],"In":[56,115],"response,":[57],"increasing":[59],"number":[60],"of":[61,178],"studies":[62],"from":[63],"the":[64,70,112,116,127,164,176],"research":[65],"community":[66],"aim":[67],"explore":[69,143],"technical":[71,108],"foundations":[72],"underlying":[73],"these":[74,80,205],"powerful":[75],"systems.":[77,93],"Building":[78],"on":[79,89,185,204],"prior":[81],"efforts,":[82],"this":[83,179],"paper":[84],"presents":[85],"reproduction":[87],"report":[88],"implementing":[90],"o1-like":[91],"We":[94],"introduce":[95],"``imitate,":[97],"explore,":[98],"self-improve''":[100],"framework,":[101],"denoted":[102],"\\textbf{STILL-2},":[104],"our":[106,194],"primary":[107],"approach":[109,195],"train":[111],"model.":[114],"initial":[117],"phase,":[118],"we":[119,181],"use":[120],"distilled":[121],"long-form":[122],"thought":[123],"data":[124],"fine-tune":[126],"model,":[129],"enabling":[130],"it":[131],"invoke":[133],"mode.":[136],"The":[137,189],"model":[138,165],"is":[139],"then":[140],"encouraged":[141],"challenging":[144,187],"problems":[145],"generating":[147],"multiple":[148],"rollouts,":[149],"which":[150],"can":[151],"result":[152],"increasingly":[154],"high-quality":[156],"trajectories":[157],"that":[158,193],"lead":[159],"correct":[161],"answers.":[162],"Furthermore,":[163],"undergoes":[166],"self-improvement":[167],"iteratively":[169],"refining":[170],"its":[171],"training":[172],"dataset.":[173],"To":[174],"verify":[175],"effectiveness":[177],"approach,":[180],"conduct":[182],"extensive":[183],"experiments":[184],"three":[186],"benchmarks.":[188,206],"experimental":[190],"results":[191],"demonstrate":[192],"achieves":[196],"competitive":[197],"performance":[198],"compared":[199],"industry-level":[201]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2024-12-14T00:00:00"}