{"id":"https://openalex.org/W4383473935","doi":"https://doi.org/10.48550/arxiv.2307.02485","title":"Building Cooperative Embodied Agents Modularly with Large Language Models","display_name":"Building Cooperative Embodied Agents Modularly with Large Language Models","publication_year":2023,"publication_date":"2023-07-05","ids":{"openalex":"https://openalex.org/W4383473935","doi":"https://doi.org/10.48550/arxiv.2307.02485"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2307.02485","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.02485","pdf_url":"https://arxiv.org/pdf/2307.02485","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/2307.02485","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023419859","display_name":"Hongxin Zhang","orcid":"https://orcid.org/0000-0003-2673-1365","observed_orcids":["https://orcid.org/0000-0003-2673-1365"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Hongxin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101541718","display_name":"Weihua Du","orcid":"https://orcid.org/0000-0002-8856-0277","observed_orcids":["https://orcid.org/0000-0002-8856-0277"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Weihua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102532316","display_name":"Jiaming Shan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shan, Jiaming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016046839","display_name":"Qinhong Zhou","orcid":"https://orcid.org/0009-0003-8461-7621","observed_orcids":["https://orcid.org/0009-0003-8461-7621"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Qinhong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041777043","display_name":"Yilun Du","orcid":"https://orcid.org/0000-0001-6792-5946","observed_orcids":["https://orcid.org/0000-0001-6792-5946"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Du, Yilun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071093940","display_name":"Joshua B. Tenenbaum","orcid":"https://orcid.org/0000-0002-1925-2035","observed_orcids":["https://orcid.org/0000-0002-1925-2035","https://orcid.org/0000-0002-0138-163X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tenenbaum, Joshua B.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005908625","display_name":"Tianmin Shu","orcid":"https://orcid.org/0000-0001-5734-0653","observed_orcids":["https://orcid.org/0000-0001-5734-0653"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shu, Tianmin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5040877128","display_name":"Chuang Gan","orcid":"https://orcid.org/0000-0003-4031-5886","observed_orcids":["https://orcid.org/0000-0003-4031-5886"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gan, Chuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":52,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5551999807357788,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.5551999807357788,"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":0.19529999792575836,"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":0.07500000298023224,"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/agent-cooperation","display_name":"agent cooperation","score":0.9599999785423279},{"id":"https://openalex.org/keywords/embodied-agents","display_name":"embodied agents","score":0.8600000143051147},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9829999804496765},{"id":"https://openalex.org/keywords/decentralized-control","display_name":"decentralized control","score":0.6620000004768372},{"id":"https://openalex.org/keywords/emergent-communication","display_name":"emergent communication","score":0.7310000061988831},{"id":"https://openalex.org/keywords/gpt-4","display_name":"GPT-4","score":0.7409999966621399},{"id":"https://openalex.org/keywords/long-horizon-planning","display_name":"long-horizon planning","score":0.6970000267028809},{"id":"https://openalex.org/keywords/human-agent-interaction","display_name":"human-agent interaction","score":0.9070000052452087}],"concepts":[{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.9619570970535278},{"id":"https://openalex.org/C103683099","wikidata":"https://www.wikidata.org/wiki/Q5370102","display_name":"Embodied agent","level":3,"score":0.7812556028366089},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.4925311505794525},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46759316325187683},{"id":"https://openalex.org/C2780966255","wikidata":"https://www.wikidata.org/wiki/Q5474306","display_name":"Foundation (evidence)","level":2,"score":0.4487518072128296},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33809804916381836},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.21058854460716248},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16807138919830322},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.08336570858955383},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2307.02485","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.02485","pdf_url":"https://arxiv.org/pdf/2307.02485","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.2307.02485","doi":"https://doi.org/10.48550/arxiv.2307.02485","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2307.02485","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:2307.02485","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2307.02485","pdf_url":"https://arxiv.org/pdf/2307.02485","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":[],"sustainable_development_goals_aurora":[{"score":0.5600000023841858,"display_name":"Partnerships for the goals","id":"https://metadata.un.org/sdg/17"}],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7166528241","https://openalex.org/W4404397197","https://openalex.org/W7118021626","https://openalex.org/W7214847469","https://openalex.org/W4413156282","https://openalex.org/W4417128642","https://openalex.org/W4412888844","https://openalex.org/W4417216537","https://openalex.org/W4389523767","https://openalex.org/W7083693340"],"abstract_inverted_index":{"In":[0],"this":[1],"work,":[2],"we":[3,43,125],"address":[4],"challenging":[5],"multi-agent":[6,181],"cooperation":[7],"problems":[8],"with":[9,40,69,88,129,132,168],"decentralized":[10],"control,":[11],"raw":[12],"sensory":[13],"observations,":[14,42],"costly":[15],"communication,":[16],"and":[17,52,58,72,86,99,112,135,152,164],"multi-objective":[18],"tasks":[19,93],"instantiated":[20],"in":[21,157,180],"various":[22],"embodied":[23],"environments.":[24],"While":[25],"previous":[26],"research":[27,171,179],"either":[28],"presupposes":[29],"a":[30,37,63,76,127,146],"cost-free":[31],"communication":[32],"channel":[33],"or":[34],"relies":[35],"on":[36,97,187],"centralized":[38],"controller":[39],"shared":[41],"harness":[44],"the":[45,173,188],"commonsense":[46],"knowledge,":[47],"reasoning":[48],"ability,":[49],"language":[50,159],"comprehension,":[51],"text":[53],"generation":[54],"prowess":[55],"of":[56,175],"LLMs":[57,176],"seamlessly":[59],"incorporate":[60],"them":[61],"into":[62],"cognitive-inspired":[64],"modular":[65],"framework":[66],"that":[67,102,154],"integrates":[68],"perception,":[70],"memory,":[71],"execution.":[73],"Thus":[74],"building":[75],"Cooperative":[77],"Embodied":[78],"Language":[79],"Agent":[80],"CoELA,":[81],"who":[82],"can":[83,107,139,160,184],"plan,":[84],"communicate,":[85],"cooperate":[87,165],"others":[89],"to":[90],"accomplish":[91],"long-horizon":[92],"efficiently.":[94],"Our":[95,170],"experiments":[96],"C-WAH":[98],"TDW-MAT":[100],"demonstrate":[101],"CoELA":[103,128,155],"driven":[104],"by":[105],"GPT-4":[106],"surpass":[108],"strong":[109],"planning-based":[110],"methods":[111],"exhibit":[113],"emergent":[114],"effective":[115],"communication.":[116],"Though":[117],"current":[118],"Open":[119],"LMs":[120],"like":[121],"LLAMA-2":[122],"still":[123],"underperform,":[124],"fine-tune":[126],"data":[130],"collected":[131],"our":[133],"agents":[134],"show":[136],"how":[137],"they":[138],"achieve":[140],"promising":[141],"performance.":[142],"We":[143],"also":[144],"conducted":[145],"user":[147],"study":[148],"for":[149,177],"human-agent":[150],"interaction":[151],"discovered":[153],"communicating":[156],"natural":[158],"earn":[161],"more":[162,166],"trust":[163],"effectively":[167],"humans.":[169],"underscores":[172],"potential":[174],"future":[178],"cooperation.":[182],"Videos":[183],"be":[185],"found":[186],"project":[189],"website":[190],"https://vis-www.cs.umass.edu/Co-LLM-Agents/.":[191]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":25},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2023-07-07T00:00:00"}