{"id":"https://openalex.org/W4407690819","doi":"https://doi.org/10.1109/tcds.2025.3543364","title":"RoboGPT: An LLM-Based Long-Term Decision-Making Embodied Agent for Instruction Following Tasks","display_name":"RoboGPT: An LLM-Based Long-Term Decision-Making Embodied Agent for Instruction Following Tasks","publication_year":2025,"publication_date":"2025-02-18","ids":{"openalex":"https://openalex.org/W4407690819","doi":"https://doi.org/10.1109/tcds.2025.3543364"},"language":"en","primary_location":{"id":"doi:10.1109/tcds.2025.3543364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3543364","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-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/A5053853035","display_name":"Yaran Chen","orcid":"https://orcid.org/0000-0001-9356-0610"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yaran Chen","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9356-0610","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenbo Cui","orcid":"https://orcid.org/0000-0001-6966-6538"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Cui","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6966-6538","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Yuanwen Chen","orcid":"https://orcid.org/0009-0004-0537-7074"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuanwen Chen","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0004-0537-7074","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108881327","display_name":"Mining Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mining Tan","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-1504-6169","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003411085","display_name":"Zhang Xinyao","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinyao Zhang","raw_affiliation_strings":["Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0005-9276-5792","affiliations":[{"raw_affiliation_string":"Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jinrui Liu","orcid":"https://orcid.org/0009-0006-2797-5408"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jinrui Liu","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-2797-5408","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoran Li","orcid":"https://orcid.org/0000-0003-2559-9585"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoran Li","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2559-9585","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624298","display_name":"Dongbin Zhao","orcid":"https://orcid.org/0000-0001-8218-9633"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongbin Zhao","raw_affiliation_strings":["State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8218-9633","affiliations":[{"raw_affiliation_string":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I19820366"]}]},{"author_position":"last","author":{"id":null,"display_name":"He Wang","orcid":"https://orcid.org/0000-0002-3365-4620"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"He Wang","raw_affiliation_strings":["Center on Frontiers of Computing Studies, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3365-4620","affiliations":[{"raw_affiliation_string":"Center on Frontiers of Computing Studies, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5053853035"],"corresponding_institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"],"apc_list":null,"apc_paid":null,"fwci":12.0032,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.98162635,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"17","issue":"5","first_page":"1163","last_page":"1174"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11122","display_name":"Online Learning and Analytics","score":0.879800021648407,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11122","display_name":"Online Learning and Analytics","score":0.879800021648407,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":0.7759000062942505,"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/T10456","display_name":"Multi-Agent Systems and Negotiation","score":0.7468000054359436,"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":0.8441989421844482},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.826448380947113},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.688129186630249},{"id":"https://openalex.org/keywords/embodied-agent","display_name":"Embodied agent","score":0.4889470338821411},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4290824234485626},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27381080389022827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8441989421844482},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.826448380947113},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.688129186630249},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.4889470338821411},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4290824234485626},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27381080389022827},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcds.2025.3543364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcds.2025.3543364","pdf_url":null,"source":{"id":"https://openalex.org/S2488537894","display_name":"IEEE Transactions on Cognitive and Developmental Systems","issn_l":"2379-8920","issn":["2379-8920","2379-8939"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Cognitive and Developmental Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.6700000166893005,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G644626782","display_name":null,"funder_award_id":"62173324","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W1999244633","https://openalex.org/W2091138122","https://openalex.org/W2963150697","https://openalex.org/W3034758614","https://openalex.org/W3085725020","https://openalex.org/W3096390127","https://openalex.org/W3150583184","https://openalex.org/W3167070827","https://openalex.org/W4205178067","https://openalex.org/W4214700710","https://openalex.org/W4285306713","https://openalex.org/W4312436794","https://openalex.org/W4312709198","https://openalex.org/W4382466695","https://openalex.org/W4383097638","https://openalex.org/W4383108457","https://openalex.org/W4385572634","https://openalex.org/W4388660746","https://openalex.org/W4389665359","https://openalex.org/W4390873374","https://openalex.org/W4390874280","https://openalex.org/W4393032096","https://openalex.org/W4394698426","https://openalex.org/W4394828156","https://openalex.org/W4402667043","https://openalex.org/W4414079285"],"related_works":["https://openalex.org/W1592154258","https://openalex.org/W1601503673","https://openalex.org/W1527882169","https://openalex.org/W4388039923","https://openalex.org/W2096246921","https://openalex.org/W2145935766","https://openalex.org/W2075610150","https://openalex.org/W2136562935","https://openalex.org/W2185743013","https://openalex.org/W1595897272"],"abstract_inverted_index":{"Robotic":[0],"agents":[1],"are":[2],"tasked":[3],"with":[4,105,134],"mastering":[5],"common":[6],"sense":[7],"and":[8,41,53,153,156,192,227],"making":[9],"long-term":[10,87],"sequential":[11],"decisions":[12,88],"to":[13,74,85,128,150],"execute":[14],"daily":[15,225],"tasks":[16,112,226,229],"based":[17,166],"on":[18,167],"natural":[19],"language":[20,26],"instructions.":[21],"Recent":[22],"advancements":[23],"in":[24,196,215],"large":[25],"models":[27],"(LLMs)":[28],"have":[29],"catalyzed":[30],"efforts":[31],"for":[32,89,147,221],"complex":[33],"robotic":[34,120],"planning.":[35],"However,":[36],"despite":[37],"their":[38],"superior":[39],"generalization":[40,136],"comprehension":[42],"capabilities,":[43],"LLM":[44],"task":[45,218],"plans":[46],"sometimes":[47],"suffer":[48],"from":[49,230],"issues":[50],"of":[51,140,207,217,223],"accuracy":[52],"feasibility.":[54],"To":[55],"address":[56],"these":[57],"challenges,":[58],"we":[59],"propose":[60],"RoboGPT,<xref":[61],"ref-type=\"fn\"":[62],"rid=\"fn1\"":[63],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[64,67],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><sup>1</sup></xref><fn":[65],"id=\"fn1\"":[66],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><label><sup>1</sup></label>":[68],"For":[69],"more":[70],"details,":[71],"please":[72],"refer":[73],"our":[75],"project":[76],"page":[77],"<uri>https://github.com/Cwb0106/RoboGPT</uri>.":[78],"</fn>":[79],"an":[80,100],"embodied":[81,107],"agent":[82],"specifically":[83],"designed":[84],"make":[86],"instruction":[90,141],"following":[91,142],"tasks.":[92],"RoboGPT":[93,203],"integrates":[94],"three":[95],"key":[96],"modules:":[97],"1)":[98],"RoboPlanner,":[99],"LLM-based":[101,213],"planning":[102,108,219],"module":[103,160],"equipped":[104],"67k":[106],"data,":[109],"breaks":[110],"down":[111],"into":[113],"logical":[114],"subgoals.":[115],"We":[116],"compile":[117],"a":[118,123,159],"new":[119],"dataset":[121],"using":[122],"template":[124],"feedback-based":[125],"self-instruction":[126],"method":[127],"fine-tune":[129],"the":[130,164,173,180,188,193,197,205],"Llama":[131],"model.":[132],"RoboPlanner":[133],"strong":[135],"can":[137,183],"plan":[138],"hundreds":[139,222],"tasks;":[143],"2)":[144],"RoboSkill,":[145,179],"customized":[146],"each":[148],"subgoal":[149],"improve":[151],"navigation":[152],"manipulation":[154],"capabilities;":[155],"3)":[157],"Re-Plan,":[158],"that":[161,202],"dynamically":[162],"adjusts":[163],"subgoals":[165,191],"real-time":[168],"environmental":[169],"feedback.":[170],"By":[171],"utilizing":[172],"precise":[174],"semantic":[175],"map":[176],"generated":[177],"by":[178,186],"target":[181],"objects":[182,194],"be":[184],"replaced":[185],"calculating":[187],"similarity":[189],"between":[190],"present":[195],"environment.":[198],"Experimental":[199],"results":[200],"demonstrate":[201],"exceeds":[204],"performance":[206],"other":[208,231],"state-of-the-art":[209],"(SOTA)":[210],"methods,":[211,214],"particularly":[212],"terms":[216],"rationality":[220],"unseen":[224],"even":[228],"domains.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":6}],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}
