{"id":"https://openalex.org/W4416748860","doi":"https://doi.org/10.1109/iros60139.2025.11247340","title":"MALMM: Multi-Agent Large Language Models for Zero-Shot Robotic Manipulation","display_name":"MALMM: Multi-Agent Large Language Models for Zero-Shot Robotic Manipulation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4416748860","doi":"https://doi.org/10.1109/iros60139.2025.11247340"},"language":null,"primary_location":{"id":"doi:10.1109/iros60139.2025.11247340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5103106106","display_name":"Harsh Singh","orcid":"https://orcid.org/0000-0003-2146-4341"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Harsh Singh","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence,UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056125162","display_name":"Rocktim Jyoti Das","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Rocktim Jyoti Das","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence,UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066841335","display_name":"Mingfei Han","orcid":"https://orcid.org/0000-0002-6036-6309"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mingfei Han","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence,UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012055259","display_name":"Preslav Nakov","orcid":"https://orcid.org/0000-0002-3600-1510"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Preslav Nakov","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence,UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087781064","display_name":"Ivan Laptev","orcid":"https://orcid.org/0000-0001-7072-3325"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Ivan Laptev","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence,UAE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence,UAE","institution_ids":["https://openalex.org/I4210113480"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210113480"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"20386","last_page":"20393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.35179999470710754,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.35179999470710754,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.14270000159740448,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.07680000364780426,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/robotics","display_name":"Robotics","score":0.6049000024795532},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5192000269889832},{"id":"https://openalex.org/keywords/supervisor","display_name":"Supervisor","score":0.5103999972343445},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.4984000027179718},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.45989999175071716},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.4016999900341034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7128999829292297},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6718000173568726},{"id":"https://openalex.org/C34413123","wikidata":"https://www.wikidata.org/wiki/Q170978","display_name":"Robotics","level":3,"score":0.6049000024795532},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5192000269889832},{"id":"https://openalex.org/C2779110517","wikidata":"https://www.wikidata.org/wiki/Q1240788","display_name":"Supervisor","level":2,"score":0.5103999972343445},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.4984000027179718},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.45989999175071716},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.4016999900341034},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.38339999318122864},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.38280001282691956},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3702000081539154},{"id":"https://openalex.org/C150415221","wikidata":"https://www.wikidata.org/wiki/Q40687","display_name":"Robotic arm","level":2,"score":0.3531000018119812},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26330000162124634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros60139.2025.11247340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros60139.2025.11247340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W100554921","https://openalex.org/W4390872747","https://openalex.org/W4391836239","https://openalex.org/W4401417048","https://openalex.org/W4402684150"],"related_works":[],"abstract_inverted_index":{"Large":[0,56],"Language":[1,57],"Models":[2],"(LLMs)":[3],"have":[4],"demonstrated":[5],"remarkable":[6],"planning":[7,65,73],"abilities":[8],"across":[9,66],"various":[10],"domains,":[11],"including":[12],"robotic":[13],"manipulation":[14,132],"and":[15,26,37,78,96,115,134],"navigation.":[16],"While":[17],"recent":[18],"work":[19],"in":[20,41,127,140,156],"robotics":[21],"deploys":[22],"LLMs":[23],"for":[24,59],"high-level":[25,72],"low-level":[27,75],"planning,":[28],"existing":[29,101,136],"methods":[30,139],"often":[31],"face":[32],"challenges":[33],"with":[34,147],"failure":[35],"recovery":[36],"suffer":[38],"from":[39],"hallucinations":[40],"long-horizon":[42,131],"tasks.":[43,119],"To":[44],"address":[45],"these":[46],"limitations,":[47],"we":[48],"propose":[49],"a":[50,79,143],"novel":[51],"multi-agent":[52],"LLM":[53,69],"framework,":[54],"Multi-Agent":[55],"Model":[58],"Manipulation":[60],"(MALMM).":[61],"Notably,":[62],"MALMM":[63,103,123],"distributes":[64],"three":[67],"specialized":[68],"agents,":[70],"namely":[71],"agent,":[74,77],"control":[76],"supervisor":[80],"agent.":[81],"Moreover,":[82],"by":[83,142],"incorporating":[84],"environment":[85],"observations":[86],"after":[87],"each":[88],"step,":[89],"our":[90,121,154],"framework":[91],"effectively":[92],"handles":[93],"intermediate":[94],"failures":[95],"enables":[97],"adaptive":[98],"re-planning.":[99],"Unlike":[100],"methods,":[102],"does":[104],"not":[105],"rely":[106],"on":[107],"pre-trained":[108],"skill":[109],"policies":[110],"or":[111],"in-context":[112],"learning":[113],"examples":[114],"generalizes":[116],"to":[117],"unseen":[118,130],"In":[120],"experiments,":[122],"demonstrates":[124],"excellent":[125],"performance":[126],"solving":[128],"previously":[129],"tasks,":[133],"outperforms":[135],"zero-shot":[137],"LLM-based":[138],"RLBench":[141],"large":[144],"margin.":[145],"Experiments":[146],"the":[148],"Franka":[149],"robot":[150],"arm":[151],"further":[152],"validate":[153],"approach":[155],"real-world":[157],"settings.":[158]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-11-28T00:00:00"}
