{"id":"https://openalex.org/W4404649409","doi":"https://doi.org/10.48550/arxiv.2411.14405","title":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions","display_name":"Marco-o1: Towards Open Reasoning Models for Open-Ended Solutions","publication_year":2024,"publication_date":"2024-11-21","ids":{"openalex":"https://openalex.org/W4404649409","doi":"https://doi.org/10.48550/arxiv.2411.14405"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.14405","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.14405","pdf_url":"https://arxiv.org/pdf/2411.14405","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/2411.14405","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115591855","display_name":"Yu Zhao","orcid":"https://orcid.org/0000-0002-7482-3742","observed_orcids":["https://orcid.org/0000-0002-7482-3742"]},"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":"Zhao, Yu","raw_affiliation_strings":["MarcoPolo Team , Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MarcoPolo Team , Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yin, Huifeng","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":"Yin, Huifeng","raw_affiliation_strings":["MarcoPolo Team , Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MarcoPolo Team , Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zeng, Bo","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":"Zeng, Bo","raw_affiliation_strings":["MarcoPolo Team , Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MarcoPolo Team , Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115695341","display_name":"Hao Wang","orcid":"https://orcid.org/0009-0008-4494-6793","observed_orcids":["https://orcid.org/0009-0008-4494-6793","https://orcid.org/0009-0003-7005-0361","https://orcid.org/0009-0000-9686-9285","https://orcid.org/0009-0002-0051-6157","https://orcid.org/0009-0009-5435-8458"]},"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":"Wang, Hao","raw_affiliation_strings":["MarcoPolo Team , Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MarcoPolo Team , Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Shi, Tianqi","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":"Shi, Tianqi","raw_affiliation_strings":["MarcoPolo Team , Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MarcoPolo Team , Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Lyu, Chenyang","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":"Lyu, Chenyang","raw_affiliation_strings":["MarcoPolo Team , Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MarcoPolo Team , 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":"Wang, Longyue","raw_affiliation_strings":["MarcoPolo Team , Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MarcoPolo Team , 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":"Luo, Weihua","raw_affiliation_strings":["MarcoPolo Team , Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MarcoPolo Team , Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103619995","display_name":"Kaifu Zhang","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":"Zhang, Kaifu","raw_affiliation_strings":["MarcoPolo Team , Alibaba International Digital Commerce"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"MarcoPolo Team , Alibaba International Digital Commerce","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I45928872"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":5,"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":0.614300012588501,"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":0.614300012588501,"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":0.16429999470710754,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.08030000329017639,"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/openai-o1","display_name":"OpenAI o1","score":0.8600000143051147},{"id":"https://openalex.org/keywords/large-reasoning-models","display_name":"large reasoning models","score":0.9369999766349792},{"id":"https://openalex.org/keywords/open-ended-problem-solving","display_name":"open-ended problem solving","score":0.8970000147819519},{"id":"https://openalex.org/keywords/chain-of-thought-fine-tuning","display_name":"chain-of-thought fine-tuning","score":0.9480000138282776},{"id":"https://openalex.org/keywords/monte-carlo-tree-search","display_name":"Monte Carlo tree search","score":0.9369999766349792},{"id":"https://openalex.org/keywords/reflection-mechanism","display_name":"reflection mechanism","score":0.8090000152587891}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49721649289131165},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.45245370268821716},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.43728604912757874},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.3400912582874298},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.339199960231781},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.3365558981895447},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.1804436445236206},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1351507604122162},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12573686242103577},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.1085628867149353},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.05804362893104553}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.14405","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.14405","pdf_url":"https://arxiv.org/pdf/2411.14405","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.2411.14405","doi":"https://doi.org/10.48550/arxiv.2411.14405","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.14405","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:2411.14405","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.14405","pdf_url":"https://arxiv.org/pdf/2411.14405","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/W4404649409.pdf","grobid_xml":"https://content.openalex.org/works/W4404649409.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4405173252","https://openalex.org/W4409393695","https://openalex.org/W4416036988","https://openalex.org/W7148684111","https://openalex.org/W4404780881","https://openalex.org/W4403579971","https://openalex.org/W7165958534","https://openalex.org/W4407686157","https://openalex.org/W4415938234","https://openalex.org/W4417298821"],"abstract_inverted_index":{"Currently":[0],"OpenAI":[1],"o1":[2,60],"sparks":[3],"a":[4],"surge":[5],"of":[6,11],"interest":[7],"in":[8],"the":[9,56,59],"study":[10],"large":[12],"reasoning":[13,94],"models":[14],"(LRM).":[15],"Building":[16],"on":[17,24,49],"this":[18],"momentum,":[19],"Marco-o1":[20,78],"not":[21],"only":[22],"focuses":[23],"disciplines":[25],"with":[26],"standard":[27],"answers,":[28],"such":[29],"as":[30],"mathematics,":[31],"physics,":[32],"and":[33,72,92],"coding":[34],"--":[35,43,96],"which":[36],"are":[37,70,74],"well-suited":[38],"for":[39,98],"reinforcement":[40],"learning":[41],"(RL)":[42],"but":[44],"also":[45],"places":[46],"greater":[47],"emphasis":[48],"open-ended":[50],"resolutions.":[51],"We":[52],"aim":[53],"to":[54,64,76],"address":[55],"question:":[57],"''Can":[58],"model":[61],"effectively":[62],"generalize":[63],"broader":[65],"domains":[66],"where":[67],"clear":[68],"standards":[69],"absent":[71],"rewards":[73],"challenging":[75],"quantify?''":[77],"is":[79],"powered":[80],"by":[81],"Chain-of-Thought":[82],"(CoT)":[83],"fine-tuning,":[84],"Monte":[85],"Carlo":[86],"Tree":[87],"Search":[88],"(MCTS),":[89],"reflection":[90],"mechanisms,":[91],"innovative":[93],"strategies":[95],"optimized":[97],"complex":[99],"real-world":[100],"problem-solving":[101],"tasks.":[102]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":3}],"updated_date":"2026-10-29T09:56:32.521200","created_date":"2024-11-24T00:00:00"}
