{"id":"https://openalex.org/W4406231668","doi":"https://doi.org/10.48550/arxiv.2501.04682","title":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","display_name":"Towards System 2 Reasoning in LLMs: Learning How to Think With Meta Chain-of-Thought","publication_year":2025,"publication_date":"2025-01-08","ids":{"openalex":"https://openalex.org/W4406231668","doi":"https://doi.org/10.48550/arxiv.2501.04682"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2501.04682","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.04682","pdf_url":"https://arxiv.org/pdf/2501.04682","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2501.04682","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023185054","display_name":"Violet Xiang","orcid":"https://orcid.org/0000-0002-1584-6231","observed_orcids":["https://orcid.org/0000-0002-1584-6231"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiang, Violet","raw_affiliation_strings":["Stanford University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University ,","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052858739","display_name":"Charlie Snell","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Snell, Charlie","raw_affiliation_strings":["UC Berkeley"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"UC Berkeley","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085625870","display_name":"Kanishk Gandhi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gandhi, Kanishk","raw_affiliation_strings":["Stanford University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University ,","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090026363","display_name":"Alon Albalak","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Albalak, Alon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088818925","display_name":"Anikait Singh","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Singh, Anikait","raw_affiliation_strings":["Stanford University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University ,","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Blagden, Chase","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Blagden, Chase","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003505678","display_name":"Duy Phung","orcid":"https://orcid.org/0009-0006-0199-6016","observed_orcids":["https://orcid.org/0009-0006-0199-6016"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phung, Duy","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028522433","display_name":"Rafael Rafailov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rafailov, Rafael","raw_affiliation_strings":["Stanford University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University ,","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093931915","display_name":"Nathan Lile","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lile, Nathan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5094363682","display_name":"Dakota Mahan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mahan, Dakota","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004714414","display_name":"Louis Castricato","orcid":"https://orcid.org/0000-0003-2996-886X","observed_orcids":["https://orcid.org/0000-0003-2996-886X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Castricato, Louis","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046536754","display_name":"Jan-Philipp Fr\u00e4nken","orcid":"https://orcid.org/0000-0001-5467-1887","observed_orcids":["https://orcid.org/0000-0001-5467-1887"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franken, Jan-Philipp","raw_affiliation_strings":["Stanford University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University ,","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069105490","display_name":"Nick Haber","orcid":"https://orcid.org/0000-0001-8804-7804","observed_orcids":["https://orcid.org/0000-0001-8804-7804"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haber, Nick","raw_affiliation_strings":["Stanford University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University ,","institution_ids":["https://openalex.org/I97018004"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005431772","display_name":"Chelsea Finn","orcid":"https://orcid.org/0000-0001-6298-0874","observed_orcids":["https://orcid.org/0000-0001-6298-0874"]},"institutions":[{"id":"https://openalex.org/I97018004","display_name":"Stanford University","ror":"https://ror.org/00f54p054","country_code":"US","type":"education","lineage":["https://openalex.org/I97018004"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Finn, Chelsea","raw_affiliation_strings":["Stanford University ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stanford University ,","institution_ids":["https://openalex.org/I97018004"]}]}],"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":0.7656000256538391,"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":0.7656000256538391,"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":0.052000001072883606,"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":0.028200000524520874,"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/chain-of-thought-reasoning","display_name":"chain-of-thought reasoning","score":0.906000018119812},{"id":"https://openalex.org/keywords/system-2-reasoning","display_name":"System 2 reasoning","score":0.8090000152587891},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9169999957084656},{"id":"https://openalex.org/keywords/process-supervision","display_name":"process supervision","score":0.921999990940094},{"id":"https://openalex.org/keywords/synthetic-data-generation","display_name":"synthetic data generation","score":0.8349999785423279},{"id":"https://openalex.org/keywords/search-algorithms","display_name":"search algorithms","score":0.7149999737739563},{"id":"https://openalex.org/keywords/instruction-tuning","display_name":"instruction tuning","score":0.8479999899864197},{"id":"https://openalex.org/keywords/reinforcement-learning-post-training","display_name":"reinforcement learning post-training","score":0.8880000114440918},{"id":"https://openalex.org/keywords/scaling-laws","display_name":"scaling laws","score":0.7680000066757202},{"id":"https://openalex.org/keywords/human-like-reasoning","display_name":"human-like reasoning","score":0.5720000267028809}],"concepts":[{"id":"https://openalex.org/C2781002164","wikidata":"https://www.wikidata.org/wiki/Q6822311","display_name":"Meta learning (computer science)","level":3,"score":0.5384632349014282},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.4817214608192444},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.3898944854736328},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.32154032588005066},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.1778348684310913},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.1286858320236206},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.06770902872085571},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2501.04682","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.04682","pdf_url":"https://arxiv.org/pdf/2501.04682","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2501.04682","doi":"https://doi.org/10.48550/arxiv.2501.04682","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2501.04682","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2501.04682","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2501.04682","pdf_url":"https://arxiv.org/pdf/2501.04682","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4406231668.pdf","grobid_xml":"https://content.openalex.org/works/W4406231668.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4414137972","https://openalex.org/W4414587198","https://openalex.org/W4412944734","https://openalex.org/W4392340654","https://openalex.org/W7115559844","https://openalex.org/W7172414247","https://openalex.org/W4407184659","https://openalex.org/W4404782001","https://openalex.org/W4416034695","https://openalex.org/W4304194220"],"abstract_inverted_index":{"We":[0,26],"propose":[1],"a":[2,23,57,62,100],"novel":[3,94],"framework,":[4],"Meta":[5],"Chain-of-Thought":[6,11],"(Meta-CoT),":[7],"which":[8],"extends":[9],"traditional":[10],"(CoT)":[12],"by":[13],"explicitly":[14],"modeling":[15],"the":[16,90,111],"underlying":[17],"reasoning":[18,95,118],"required":[19],"to":[20,64,105],"arrive":[21],"at":[22],"particular":[24],"CoT.":[25],"present":[27],"empirical":[28],"evidence":[29],"from":[30],"state-of-the-art":[31],"models":[32],"exhibiting":[33],"behaviors":[34],"consistent":[35],"with":[36,70],"in-context":[37],"search,":[38],"and":[39,51,74,89,102,116],"explore":[40],"methods":[41],"for":[42,60,92,113],"producing":[43],"Meta-CoT":[44,107],"via":[45],"process":[46],"supervision,":[47],"synthetic":[48],"data":[49],"generation,":[50],"search":[52,72],"algorithms.":[53,96],"Finally,":[54,78],"we":[55,79],"outline":[56],"concrete":[58],"pipeline":[59],"training":[61],"model":[63],"produce":[65],"Meta-CoTs,":[66],"incorporating":[67],"instruction":[68],"tuning":[69],"linearized":[71],"traces":[73],"reinforcement":[75],"learning":[76],"post-training.":[77],"discuss":[80],"open":[81],"research":[82],"questions,":[83],"including":[84],"scaling":[85],"laws,":[86],"verifier":[87],"roles,":[88],"potential":[91],"discovering":[93],"This":[97],"work":[98],"provides":[99],"theoretical":[101],"practical":[103],"roadmap":[104],"enable":[106],"in":[108,119],"LLMs,":[109],"paving":[110],"way":[112],"more":[114],"powerful":[115],"human-like":[117],"artificial":[120],"intelligence.":[121]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-10-13T10:08:12.033832","created_date":"2025-01-10T00:00:00"}
