{"id":"https://openalex.org/W4403487343","doi":"https://doi.org/10.3233/faia240916","title":"Multi-Agent Planning Using Visual Language Models","display_name":"Multi-Agent Planning Using Visual Language Models","publication_year":2024,"publication_date":"2024-10-16","ids":{"openalex":"https://openalex.org/W4403487343","doi":"https://doi.org/10.3233/faia240916"},"language":"en","primary_location":{"id":"doi:10.3233/faia240916","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240916","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240916","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240916","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073429310","display_name":"Michele Brienza","orcid":"https://orcid.org/0009-0000-1549-9500"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Michele Brienza","raw_affiliation_strings":["Sapienza University of Rome, Rome RM 00181, Italy"],"raw_orcid":"https://orcid.org/0009-0000-1549-9500","affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome RM 00181, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069605954","display_name":"Francesco Argenziano","orcid":"https://orcid.org/0009-0004-2028-7253"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Francesco Argenziano","raw_affiliation_strings":["Sapienza University of Rome, Rome RM 00181, Italy"],"raw_orcid":"https://orcid.org/0009-0004-2028-7253","affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome RM 00181, Italy","institution_ids":["https://openalex.org/I861853513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030500376","display_name":"Vincenzo Suriani","orcid":"https://orcid.org/0000-0003-1199-8358"},"institutions":[{"id":"https://openalex.org/I20272500","display_name":"University of Basilicata","ror":"https://ror.org/03tc05689","country_code":"IT","type":"education","lineage":["https://openalex.org/I20272500"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Vincenzo Suriani","raw_affiliation_strings":["University of Basilicata, Potenza PZ 85100, Italy"],"raw_orcid":"https://orcid.org/0000-0003-1199-8358","affiliations":[{"raw_affiliation_string":"University of Basilicata, Potenza PZ 85100, Italy","institution_ids":["https://openalex.org/I20272500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012452119","display_name":"Domenico D. Bloisi","orcid":"https://orcid.org/0000-0003-0339-8651"},"institutions":[{"id":"https://openalex.org/I4210135106","display_name":"Universit\u00e0 degli Studi Internazionali di Roma","ror":"https://ror.org/037263487","country_code":"IT","type":"education","lineage":["https://openalex.org/I4210135106"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Domenico D. Bloisi","raw_affiliation_strings":["International University of Rome UNINT, Rome RM 00147, Italy"],"raw_orcid":"https://orcid.org/0000-0003-0339-8651","affiliations":[{"raw_affiliation_string":"International University of Rome UNINT, Rome RM 00147, Italy","institution_ids":["https://openalex.org/I4210135106"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075651762","display_name":"Daniele Nardi","orcid":"https://orcid.org/0000-0001-6606-200X"},"institutions":[{"id":"https://openalex.org/I861853513","display_name":"Sapienza University of Rome","ror":"https://ror.org/02be6w209","country_code":"IT","type":"education","lineage":["https://openalex.org/I861853513"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Daniele Nardi","raw_affiliation_strings":["Sapienza University of Rome, Rome RM 00181, Italy"],"raw_orcid":"https://orcid.org/0000-0001-6606-200X","affiliations":[{"raw_affiliation_string":"Sapienza University of Rome, Rome RM 00181, Italy","institution_ids":["https://openalex.org/I861853513"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5073429310"],"corresponding_institution_ids":["https://openalex.org/I861853513"],"apc_list":null,"apc_paid":null,"fwci":1.1221,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.85341402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7267000079154968,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7267000079154968,"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"}},{"id":"https://openalex.org/T10100","display_name":"Metaheuristic Optimization Algorithms Research","score":0.675000011920929,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.6624000072479248,"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":0.599319577217102},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34282827377319336},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.337928831577301}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.599319577217102},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34282827377319336},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.337928831577301}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.3233/faia240916","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240916","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240916","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:iris.unibas.it:11563/204561","is_oa":false,"landing_page_url":"https://hdl.handle.net/11563/204561","pdf_url":null,"source":{"id":"https://openalex.org/S4377196360","display_name":"CINECA IRIS Institutional Research Information System (University of Basilicata)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I20272500","host_organization_name":"University of Basilicata","host_organization_lineage":["https://openalex.org/I20272500"],"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":"info:eu-repo/semantics/conferenceObject"},{"id":"pmh:oai:iris.uniroma1.it:11573/1725810","is_oa":false,"landing_page_url":"https://hdl.handle.net/11573/1725810","pdf_url":null,"source":{"id":"https://openalex.org/S4377196107","display_name":"IRIS Research product catalog (Sapienza University of Rome)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3233/faia240916","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia240916","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/FAIA240916","source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403487343.pdf"},"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":{"Large":[0],"Language":[1,6],"Models":[2,7],"(LLMs)":[3],"and":[4,18,23,27,48,73],"Visual":[5],"(VLMs)":[8],"are":[9,50,70],"attracting":[10],"increasing":[11],"interest":[12],"due":[13],"to":[14,146,166,171],"their":[15],"improving":[16],"performance":[17],"applications":[19],"across":[20],"various":[21],"domains":[22,130],"tasks.":[24],"However,":[25],"LLMs":[26],"VLMs":[28],"can":[29,89],"produce":[30],"erroneous":[31],"results,":[32],"especially":[33],"when":[34,46],"a":[35,101,122,138,152],"deep":[36],"understanding":[37],"of":[38,58,125,151,176],"the":[39,80,92,111,126,149,159,167,174,177],"problem":[40],"domain":[41],"is":[42],"required.":[43],"For":[44],"instance,":[45],"planning":[47,107],"perception":[49],"needed":[51],"simultaneously,":[52],"these":[53],"models":[54,69],"often":[55],"struggle":[56],"because":[57],"difficulties":[59],"in":[60],"merging":[61],"multi-modal":[62],"information.":[63],"To":[64],"address":[65],"this":[66,97],"issue,":[67],"fine-tuned":[68],"typically":[71],"employed":[72],"trained":[74],"on":[75],"specialized":[76],"data":[77,115],"structures":[78,116],"representing":[79],"environment.":[81],"This":[82],"approach":[83,157],"has":[84],"limited":[85],"effectiveness,":[86],"as":[87,117],"it":[88,120],"overly":[90],"complicate":[91],"context":[93],"for":[94,104,113],"processing.":[95],"In":[96],"paper,":[98],"we":[99],"propose":[100],"multi-agent":[102],"architecture":[103],"embodied":[105],"task":[106],"that":[108],"operates":[109],"without":[110],"need":[112],"specific":[114],"input.":[118],"Instead,":[119],"uses":[121],"single":[123],"image":[124],"environment,":[127],"handling":[128],"free-form":[129],"by":[131],"leveraging":[132],"commonsense":[133],"knowledge.":[134],"We":[135,154],"also":[136],"introduce":[137],"novel,":[139],"fully":[140],"automatic":[141],"evaluation":[142],"procedure,":[143],"PG2S,":[144],"designed":[145],"better":[147],"assess":[148],"quality":[150,175],"plan.":[153],"validated":[155],"our":[156],"using":[158],"widely":[160],"recognized":[161],"ALFRED":[162],"dataset,":[163],"comparing":[164],"PG2S":[165],"existing":[168],"KAS":[169],"metric":[170],"further":[172],"evaluate":[173],"generated":[178],"plans.":[179]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}