{"id":"https:\/\/openalex.org\/W4413147426","doi":"https:\/\/doi.org\/10.1109\/cvpr52734.2025.00845","title":"Optimus-2 : Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy","display_name":"Optimus-2 : Multimodal Minecraft Agent with Goal-Observation-Action Conditioned Policy","publication_year":2025,"publication_date":"2025-06-10","ids":{"openalex":"https:\/\/openalex.org\/W4413147426","doi":"https:\/\/doi.org\/10.1109\/cvpr52734.2025.00845"},"language":"en","primary_location":{"id":"doi:10.1109\/cvpr52734.2025.00845","is_oa":false,"landing_page_url":"https:\/\/doi.org\/10.1109\/cvpr52734.2025.00845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https:\/\/openalex.org\/A5111113724","display_name":"Zaijing Li","orcid":null},"institutions":[{"id":"https:\/\/openalex.org\/I204983213","display_name":"Harbin Institute of Technology","ror":"https:\/\/ror.org\/01yqg2h08","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I204983213"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zaijing Li","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https:\/\/openalex.org\/I204983213"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuquan Xie","orcid":null},"institutions":[{"id":"https:\/\/openalex.org\/I204983213","display_name":"Harbin Institute of Technology","ror":"https:\/\/ror.org\/01yqg2h08","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuquan Xie","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https:\/\/openalex.org\/I204983213"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5037878863","display_name":"Rui Shao","orcid":"https:\/\/orcid.org\/0000-0003-0090-9604"},"institutions":[{"id":"https:\/\/openalex.org\/I204983213","display_name":"Harbin Institute of Technology","ror":"https:\/\/ror.org\/01yqg2h08","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Shao","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https:\/\/openalex.org\/I204983213"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5007109976","display_name":"Gongwei Chen","orcid":"https:\/\/orcid.org\/0000-0002-0634-6075"},"institutions":[{"id":"https:\/\/openalex.org\/I204983213","display_name":"Harbin Institute of Technology","ror":"https:\/\/ror.org\/01yqg2h08","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gongwei Chen","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https:\/\/openalex.org\/I204983213"]}]},{"author_position":"middle","author":{"id":"https:\/\/openalex.org\/A5102021513","display_name":"Dongmei Jiang","orcid":"https:\/\/orcid.org\/0000-0002-2737-5537"},"institutions":[{"id":"https:\/\/openalex.org\/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https:\/\/ror.org\/03qdqbt06","country_code":"CN","type":"facility","lineage":["https:\/\/openalex.org\/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Jiang","raw_affiliation_strings":["Peng Cheng Laboratory"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory","institution_ids":["https:\/\/openalex.org\/I4210136793"]}]},{"author_position":"last","author":{"id":"https:\/\/openalex.org\/A5038612499","display_name":"Liqiang Nie","orcid":"https:\/\/orcid.org\/0000-0003-1476-0273"},"institutions":[{"id":"https:\/\/openalex.org\/I204983213","display_name":"Harbin Institute of Technology","ror":"https:\/\/ror.org\/01yqg2h08","country_code":"CN","type":"education","lineage":["https:\/\/openalex.org\/I204983213"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liqiang Nie","raw_affiliation_strings":["Harbin Institute of Technology,Shenzhen"],"affiliations":[{"raw_affiliation_string":"Harbin Institute of Technology,Shenzhen","institution_ids":["https:\/\/openalex.org\/I204983213"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https:\/\/openalex.org\/A5111113724"],"corresponding_institution_ids":["https:\/\/openalex.org\/I204983213"],"apc_list":null,"apc_paid":null,"fwci":0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10097553,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"9039","last_page":"9049"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https:\/\/openalex.org\/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9606000185012817,"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\/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.9606000185012817,"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\/computer-science","display_name":"Computer science","score":0.6541522741317749},{"id":"https:\/\/openalex.org\/keywords\/action","display_name":"Action (physics)","score":0.5516279935836792},{"id":"https:\/\/openalex.org\/keywords\/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.34253525733947754},{"id":"https:\/\/openalex.org\/keywords\/physics","display_name":"Physics","score":0.08665680885314941}],"concepts":[{"id":"https:\/\/openalex.org\/C41008148","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q21198","display_name":"Computer science","level":0,"score":0.6541522741317749},{"id":"https:\/\/openalex.org\/C2780791683","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q846785","display_name":"Action (physics)","level":2,"score":0.5516279935836792},{"id":"https:\/\/openalex.org\/C107457646","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.34253525733947754},{"id":"https:\/\/openalex.org\/C121332964","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q413","display_name":"Physics","level":0,"score":0.08665680885314941},{"id":"https:\/\/openalex.org\/C62520636","wikidata":"https:\/\/www.wikidata.org\/wiki\/Q944","display_name":"Quantum mechanics","level":1,"score":0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109\/cvpr52734.2025.00845","is_oa":false,"landing_page_url":"https:\/\/doi.org\/10.1109\/cvpr52734.2025.00845","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","id":"https:\/\/metadata.un.org\/sdg\/13","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https:\/\/openalex.org\/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https:\/\/ror.org\/01h0zpd94"},{"id":"https:\/\/openalex.org\/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https:\/\/ror.org\/0426zh255"},{"id":"https:\/\/openalex.org\/F4320321921","display_name":"Natural Science Foundation of Guangdong Province","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"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":{"Building":[0],"an":[1,76,107],"agent":[2,52],"that":[3,53,80,109,166],"can":[4,152],"mimic":[5],"human":[6],"behavior":[7,103,111],"patterns":[8,25],"to":[9,21,117,154,158],"accomplish":[10],"various":[11],"open-world":[12],"tasks":[13,179],"is":[14],"a":[15,29,49,55,65,124],"longterm":[16],"goal.":[17],"To":[18,43],"enable":[19],"agents":[20],"effectively":[22],"learn":[23],"behavioral":[24],"across":[26,134,171],"diverse":[27],"tasks,":[28,137,173,175],"key":[30],"challenge":[31],"lies":[32],"in":[33,180],"modeling":[34],"the":[35,95,149,155,184],"intricate":[36],"relationships":[37,83],"among":[38],"observations,":[39],"actions,":[40],"and":[41,86,105,176],"language.":[42],"this":[44],"end,":[45],"we":[46,122],"propose":[47],"Optimus-2,":[48],"novel":[50],"Minecraft":[51,126,160],"incorporates":[54],"Multimodal":[56],"Large":[57],"Language":[58],"Model":[59],"(MLLM)":[60],"for":[61,70],"highlevel":[62],"planning,":[63],"alongside":[64],"Goal-Observation-Action":[66,127],"Conditioned":[67],"Policy":[68],"(GOAP)":[69],"low-level":[71],"control.":[72],"GOAP":[73],"contains":[74,131],"(1)":[75],"Action-guided":[77],"Behavior":[78],"Encoder":[79],"models":[81],"causal":[82],"between":[84],"observations":[85],"actions":[87,119],"at":[88,187],"each":[89],"timestep,":[90],"then":[91],"dynamically":[92],"interacts":[93],"with":[94,113,148],"historical":[96],"observation-action":[97],"sequence,":[98],"consolidating":[99],"it":[100],"into":[101],"fixedlength":[102],"tokens,":[104],"(2)":[106],"MLLM":[108],"aligns":[110],"tokens":[112],"open-ended":[114,177],"language":[115],"instructions":[116],"predict":[118],"auto-regressively.":[120],"Moreover,":[121],"introduce":[123],"high-quality":[125],"(MGOA)":[128],"dataset,":[129,151],"which":[130],"25,000":[132],"videos":[133],"8":[135],"atomic":[136,172],"providing":[138],"about":[139],"30M":[140],"goal-observation-action":[141],"pairs.":[142],"The":[143],"automated":[144],"construction":[145],"method,":[146],"along":[147],"MGOA":[150],"contribute":[153],"community\u2019s":[156],"efforts":[157],"train":[159],"agents.":[161],"Extensive":[162],"experimental":[163],"results":[164],"demonstrate":[165],"Optimus-2":[167],"exhibits":[168],"superior":[169],"performance":[170],"long-horizon":[174],"instruction":[178],"Minecraft.":[181],"Please":[182],"see":[183],"project":[185],"page":[186],"https:\/\/cybertronagent.github.io\/Optimus-2.github.io\/.":[188]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}