{"id":"https://openalex.org/W4294010056","doi":"https://doi.org/10.48550/arxiv.2208.13266","title":"JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents","display_name":"JARVIS: A Neuro-Symbolic Commonsense Reasoning Framework for Conversational Embodied Agents","publication_year":2022,"publication_date":"2022-08-28","ids":{"openalex":"https://openalex.org/W4294010056","doi":"https://doi.org/10.48550/arxiv.2208.13266"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2208.13266","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.13266","pdf_url":"https://arxiv.org/pdf/2208.13266","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2208.13266","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5004952111","display_name":"Kaizhi Zheng","orcid":"https://orcid.org/0000-0002-8718-1603","observed_orcids":["https://orcid.org/0000-0002-8718-1603"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng, Kaizhi","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101842986","display_name":"Kaiwen Zhou","orcid":"https://orcid.org/0009-0006-0779-5450","observed_orcids":["https://orcid.org/0009-0006-0779-5450"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhou, Kaiwen","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100370035","display_name":"Jing Gu","orcid":"https://orcid.org/0000-0002-4035-9072","observed_orcids":["https://orcid.org/0000-0002-4035-9072"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gu, Jing","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110775241","display_name":"Yue Fan","orcid":"https://orcid.org/0000-0001-6670-2011","observed_orcids":["https://orcid.org/0000-0001-6670-2011"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fan, Yue","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100603057","display_name":"Jialu Wang","orcid":"https://orcid.org/0000-0002-1844-8685","observed_orcids":["https://orcid.org/0000-0002-1844-8685","https://orcid.org/0009-0004-6793-661X"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Jialu","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014510735","display_name":"Zonglin Di","orcid":"https://orcid.org/0000-0002-3875-2676","observed_orcids":["https://orcid.org/0000-0002-3875-2676"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di, Zonglin","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101181260","display_name":"Xuehai He","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"He, Xuehai","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100328100","display_name":"Xin Eric Wang","orcid":"https://orcid.org/0000-0003-2605-5504","observed_orcids":["https://orcid.org/0000-0003-2605-5504"]},"institutions":[{"id":"https://openalex.org/I185103710","display_name":"University of California, Santa Cruz","ror":"https://ror.org/03s65by71","country_code":"US","type":"education","lineage":["https://openalex.org/I185103710"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wang, Xin Eric","raw_affiliation_strings":["University of California , Santa Cruz"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California , Santa Cruz","institution_ids":["https://openalex.org/I185103710"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I185103710"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":47,"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/T12031","display_name":"Speech and dialogue systems","score":0.5859000086784363,"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/T12031","display_name":"Speech and dialogue systems","score":0.5859000086784363,"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":0.33079999685287476,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.01850000023841858,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/neuro-symbolic-reasoning","display_name":"neuro-symbolic reasoning","score":0.9010000228881836},{"id":"https://openalex.org/keywords/commonsense-reasoning","display_name":"commonsense reasoning","score":0.9739999771118164},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6990000009536743},{"id":"https://openalex.org/keywords/semantic-maps","display_name":"semantic maps","score":0.6140000224113464},{"id":"https://openalex.org/keywords/human-agent-communication","display_name":"human-agent communication","score":0.75},{"id":"https://openalex.org/keywords/few-shot-learning","display_name":"few-shot learning","score":0.6779999732971191},{"id":"https://openalex.org/keywords/interpretability","display_name":"interpretability","score":0.6600000262260437}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7461482286453247},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5835336446762085},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.575207531452179},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.555760383605957},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.49715402722358704},{"id":"https://openalex.org/C193221554","wikidata":"https://www.wikidata.org/wiki/Q5153664","display_name":"Commonsense reasoning","level":2,"score":0.47823137044906616},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36005714535713196},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2208.13266","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.13266","pdf_url":"https://arxiv.org/pdf/2208.13266","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.2208.13266","doi":"https://doi.org/10.48550/arxiv.2208.13266","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2208.13266","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:2208.13266","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2208.13266","pdf_url":"https://arxiv.org/pdf/2208.13266","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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4294010056.pdf","grobid_xml":"https://content.openalex.org/works/W4294010056.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W2155487235","https://openalex.org/W2776202271","https://openalex.org/W2890902815","https://openalex.org/W2908510526","https://openalex.org/W2950801649","https://openalex.org/W2962887844","https://openalex.org/W2963341956","https://openalex.org/W2970340522","https://openalex.org/W2980282514","https://openalex.org/W3003391301","https://openalex.org/W3126325318","https://openalex.org/W3154984731","https://openalex.org/W3203663566","https://openalex.org/W3211887611","https://openalex.org/W4221152848","https://openalex.org/W4245138255"],"related_works":["https://openalex.org/W2289634307","https://openalex.org/W618776698","https://openalex.org/W7203681643","https://openalex.org/W2132124599","https://openalex.org/W7099058445","https://openalex.org/W4415904748","https://openalex.org/W7223225074","https://openalex.org/W3203663566","https://openalex.org/W4388514848","https://openalex.org/W4389009467"],"abstract_inverted_index":{"Building":[0],"a":[1,11,66],"conversational":[2,76],"embodied":[3,77,146],"agent":[4],"to":[5,56,175],"execute":[6],"real-life":[7],"tasks":[8],"has":[9],"been":[10],"long-standing":[12],"yet":[13],"quite":[14],"challenging":[15],"research":[16],"goal,":[17],"as":[18],"it":[19,80],"requires":[20],"effective":[21],"human-agent":[22],"communication,":[23],"multi-modal":[24],"understanding,":[25],"long-range":[26],"sequential":[27],"decision":[28],"making,":[29],"etc.":[30],"Traditional":[31],"symbolic":[32,82,106],"methods":[33],"have":[34],"scaling":[35],"and":[36,48,52,74,93,96,112,118,131,158,189],"generalization":[37],"issues,":[38],"while":[39],"end-to-end":[40],"deep":[41],"learning":[42],"models":[43,88],"suffer":[44],"from":[45,60,101,150,155,173],"data":[46],"scarcity":[47],"high":[49],"task":[50,187],"complexity,":[51],"are":[53],"often":[54],"hard":[55],"explain.":[57],"To":[58],"benefit":[59],"both":[61],"worlds,":[62],"we":[63,178],"propose":[64],"JARVIS,":[65],"neuro-symbolic":[67],"commonsense":[68],"reasoning":[69],"framework":[70],"for":[71,90,109],"modular,":[72],"generalizable,":[73],"interpretable":[75],"agents.":[78],"First,":[79],"acquires":[81],"representations":[83],"by":[84,97],"prompting":[85],"large":[86],"language":[87,91],"(LLMs)":[89],"understanding":[92],"sub-goal":[94,110],"planning,":[95],"constructing":[98],"semantic":[99],"maps":[100],"visual":[102],"observations.":[103],"Then":[104],"the":[105,125,129,167,181,186,192,206],"module":[107],"reasons":[108],"planning":[111],"action":[113],"generation":[114],"based":[115],"on":[116,124,142,171],"task-":[117],"action-level":[119],"common":[120],"sense.":[121],"Extensive":[122],"experiments":[123],"TEACh":[126],"dataset":[127],"validate":[128],"efficacy":[130],"efficiency":[132],"of":[133,194],"our":[134,164,195],"JARVIS":[135,201],"framework,":[136],"which":[137],"achieves":[138],"state-of-the-art":[139],"(SOTA)":[140],"results":[141],"all":[143],"three":[144],"dialog-based":[145],"tasks,":[147],"including":[148],"Execution":[149],"Dialog":[151,156],"History":[152],"(EDH),":[153],"Trajectory":[154],"(TfD),":[157],"Two-Agent":[159],"Task":[160],"Completion":[161],"(TATC)":[162],"(e.g.,":[163],"method":[165,196],"boosts":[166],"unseen":[168],"Success":[169],"Rate":[170],"EDH":[172],"6.1\\%":[174],"15.8\\%).":[176],"Moreover,":[177],"systematically":[179],"analyze":[180],"essential":[182],"factors":[183],"that":[184],"affect":[185],"performance":[188],"also":[190],"demonstrate":[191],"superiority":[193],"in":[197,205],"few-shot":[198],"settings.":[199],"Our":[200],"model":[202],"ranks":[203],"first":[204],"Alexa":[207],"Prize":[208],"SimBot":[209],"Public":[210],"Benchmark":[211],"Challenge.":[212]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":16},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-09-01T00:00:00"}
