{"id":"https://openalex.org/W7127358564","doi":"https://doi.org/10.48550/arxiv.2602.00675","title":"Factored Reasoning with Inner Speech and Persistent Memory for Evidence-Grounded Human-Robot Interaction","display_name":"Factored Reasoning with Inner Speech and Persistent Memory for Evidence-Grounded Human-Robot Interaction","publication_year":2026,"publication_date":"2026-01-31","ids":{"openalex":"https://openalex.org/W7127358564","doi":"https://doi.org/10.48550/arxiv.2602.00675"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2602.00675","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.00675","pdf_url":"https://arxiv.org/pdf/2602.00675","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/2602.00675","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5077880770","display_name":"Valerio Belcamino","orcid":"https://orcid.org/0000-0002-9264-8191","observed_orcids":["https://orcid.org/0000-0002-9264-8191"]},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Belcamino, Valerio","raw_affiliation_strings":["Department of Engineering , University of Palermo , Viale delle Scienze , Bldg. 7 , Palermo , 90128 , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering , University of Palermo , Viale delle Scienze , Bldg. 7 , Palermo , 90128 , Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035139597","display_name":"Mariya Kilina","orcid":"https://orcid.org/0009-0000-0630-7714","observed_orcids":["https://orcid.org/0009-0000-0630-7714"]},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Kilina, Mariya","raw_affiliation_strings":["Department of Engineering , University of Palermo , Viale delle Scienze , Bldg. 7 , Palermo , 90128 , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering , University of Palermo , Viale delle Scienze , Bldg. 7 , Palermo , 90128 , Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083539729","display_name":"Alessandro Carf\u00ec","orcid":"https://orcid.org/0000-0001-9208-6910","observed_orcids":["https://orcid.org/0000-0001-9208-6910"]},"institutions":[{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Carf\u00ec, Alessandro","raw_affiliation_strings":["TheEngineRoom , Department of Informatics Bioengineering, Robotics and System Engineering , via all'Opera Pia 13 , Genoa , 16145 , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TheEngineRoom , Department of Informatics Bioengineering, Robotics and System Engineering , via all'Opera Pia 13 , Genoa , 16145 , Italy","institution_ids":["https://openalex.org/I83816512"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029938341","display_name":"Valeria Seidita","orcid":"https://orcid.org/0000-0002-0601-6914","observed_orcids":["https://orcid.org/0000-0002-0601-6914"]},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Seidita, Valeria","raw_affiliation_strings":["Department of Engineering , University of Palermo , Viale delle Scienze , Bldg. 7 , Palermo , 90128 , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering , University of Palermo , Viale delle Scienze , Bldg. 7 , Palermo , 90128 , Italy","institution_ids":["https://openalex.org/I900890020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017108129","display_name":"Fulvio Mastrogiovanni","orcid":"https://orcid.org/0000-0001-5913-1898","observed_orcids":["https://orcid.org/0000-0001-5913-1898"]},"institutions":[{"id":"https://openalex.org/I83816512","display_name":"University of Genoa","ror":"https://ror.org/0107c5v14","country_code":"IT","type":"education","lineage":["https://openalex.org/I83816512"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Mastrogiovanni, Fulvio","raw_affiliation_strings":["TheEngineRoom , Department of Informatics Bioengineering, Robotics and System Engineering , via all'Opera Pia 13 , Genoa , 16145 , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TheEngineRoom , Department of Informatics Bioengineering, Robotics and System Engineering , via all'Opera Pia 13 , Genoa , 16145 , Italy","institution_ids":["https://openalex.org/I83816512"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045147364","display_name":"Antonio Chella","orcid":"https://orcid.org/0000-0002-8625-708X","observed_orcids":["https://orcid.org/0000-0002-8625-708X"]},"institutions":[{"id":"https://openalex.org/I900890020","display_name":"University of Palermo","ror":"https://ror.org/044k9ta02","country_code":"IT","type":"education","lineage":["https://openalex.org/I900890020"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Chella, Antonio","raw_affiliation_strings":["Department of Engineering , University of Palermo , Viale delle Scienze , Bldg. 7 , Palermo , 90128 , Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Engineering , University of Palermo , Viale delle Scienze , Bldg. 7 , Palermo , 90128 , Italy","institution_ids":["https://openalex.org/I900890020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"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":0.9580000042915344,"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":0.9580000042915344,"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/T10709","display_name":"Social Robot Interaction and HRI","score":0.02759999968111515,"subfield":{"id":"https://openalex.org/subfields/3207","display_name":"Social Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10906","display_name":"AI-based Problem Solving and Planning","score":0.010499999858438969,"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/human-robot-interaction","display_name":"human-robot interaction","score":0.9509999752044678},{"id":"https://openalex.org/keywords/inner-speech","display_name":"inner speech","score":0.9319999814033508},{"id":"https://openalex.org/keywords/persistent-memory","display_name":"persistent memory","score":0.9309999942779541},{"id":"https://openalex.org/keywords/cognitive-architecture","display_name":"cognitive architecture","score":0.5419999957084656},{"id":"https://openalex.org/keywords/assistive-robots","display_name":"assistive robots","score":0.7829999923706055},{"id":"https://openalex.org/keywords/partially-observable-markov-decision-processes","display_name":"partially observable Markov decision processes","score":0.8180000185966492},{"id":"https://openalex.org/keywords/evidence-grounding","display_name":"evidence grounding","score":0.6079999804496765},{"id":"https://openalex.org/keywords/clarifying-questions","display_name":"clarification questions","score":0.5260000228881836},{"id":"https://openalex.org/keywords/memory-consolidation","display_name":"memory consolidation","score":0.6150000095367432},{"id":"https://openalex.org/keywords/semantic-search","display_name":"semantic search","score":0.6769999861717224},{"id":"https://openalex.org/keywords/knowledge-graphs","display_name":"knowledge graphs","score":0.6930000185966492},{"id":"https://openalex.org/keywords/intent-recognition","display_name":"intent classification","score":0.4560000002384186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7597000002861023},{"id":"https://openalex.org/C17098449","wikidata":"https://www.wikidata.org/wiki/Q176814","display_name":"Partially observable Markov decision process","level":4,"score":0.5371000170707703},{"id":"https://openalex.org/C20854674","wikidata":"https://www.wikidata.org/wiki/Q4386060","display_name":"Cognitive architecture","level":3,"score":0.5212000012397766},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46470001339912415},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.45329999923706055},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.40610000491142273},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.3950999975204468},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.39239999651908875},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.3847000002861023},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C161407221","wikidata":"https://www.wikidata.org/wiki/Q4382939","display_name":"Cognitive model","level":3,"score":0.3549000024795532},{"id":"https://openalex.org/C121375916","wikidata":"https://www.wikidata.org/wiki/Q936559","display_name":"Principle of compositionality","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.31679999828338623},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.31369999051094055},{"id":"https://openalex.org/C192327766","wikidata":"https://www.wikidata.org/wiki/Q1038799","display_name":"Cognitive robotics","level":3,"score":0.3089999854564667},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.27079999446868896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2671999931335449},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.26170000433921814},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.26019999384880066},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.25279998779296875},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.2515000104904175},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.25119999051094055},{"id":"https://openalex.org/C2778023277","wikidata":"https://www.wikidata.org/wiki/Q321703","display_name":"Premise","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2602.00675","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.00675","pdf_url":"https://arxiv.org/pdf/2602.00675","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.2602.00675","doi":"https://doi.org/10.48550/arxiv.2602.00675","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.00675","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.00675","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.00675","pdf_url":"https://arxiv.org/pdf/2602.00675","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/W7127358564.pdf","grobid_xml":"https://content.openalex.org/works/W7127358564.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2245778510","https://openalex.org/W2130543732","https://openalex.org/W2185715170","https://openalex.org/W2971410488","https://openalex.org/W2090118499","https://openalex.org/W2945252250","https://openalex.org/W7116858058","https://openalex.org/W7098085080","https://openalex.org/W2536425868","https://openalex.org/W7134848241"],"abstract_inverted_index":{"Dialogue-based":[0],"human-robot":[1],"interaction":[2,41,214],"requires":[3],"robot":[4,210],"cognitive":[5,34,134],"assistants":[6],"to":[7,72,158,205],"maintain":[8],"persistent":[9],"user":[10],"context,":[11],"recover":[12],"from":[13],"underspecified":[14],"requests,":[15],"and":[16,49,82,85,95,111,122,146,165,192,208],"ground":[17],"responses":[18],"in":[19,133,176],"external":[20],"evidence,":[21],"while":[22,151],"keeping":[23],"intermediate":[24],"decisions":[25],"verifiable.":[26],"In":[27],"this":[28,60],"paper":[29],"we":[30],"introduce":[31],"JANUS,":[32],"a":[33,43,53,103,107,137,152,177,183,202],"architecture":[35],"for":[36,90],"assistive":[37],"robots":[38],"that":[39,142],"models":[40],"as":[42,52,201],"partially":[44],"observable":[45],"Markov":[46],"decision":[47],"process":[48],"realizes":[50],"control":[51],"factored":[54,199],"controller":[55],"with":[56,115,189],"typed":[57],"interfaces.":[58],"To":[59],"aim,":[61],"Janus":[62],"(i)":[63],"decomposes":[64],"the":[65,128],"overall":[66],"behavior":[67],"into":[68],"specialized":[69],"modules,":[70],"related":[71],"scope":[73],"detection,":[74],"intent":[75],"recognition,":[76],"memory,":[77,110],"inner":[78,131],"speech,":[79,84],"query":[80],"generation,":[81],"outer":[83],"(ii)":[86],"exposes":[87],"explicit":[88],"policies":[89],"information":[91],"sufficiency,":[92],"execution":[93],"readiness,":[94],"tool":[96,167],"grounding.":[97],"A":[98],"dedicated":[99],"memory":[100],"agent":[101],"maintains":[102],"bounded":[104],"recent-history":[105],"buffer,":[106],"compact":[108],"core":[109],"an":[112,159],"archival":[113],"store":[114],"semantic":[116],"retrieval,":[117],"coupled":[118],"through":[119,172],"controlled":[120],"consolidation":[121],"revision":[123],"policies.":[124],"Models":[125],"inspired":[126],"by":[127],"notion":[129],"of":[130],"speech":[132],"theories":[135],"provide":[136],"control-oriented":[138],"internal":[139],"textual":[140],"flow":[141],"validates":[143],"parameter":[144],"completeness":[145],"triggers":[147],"clarification":[148],"before":[149],"grounding,":[150],"faithfulness":[153],"constraint":[154],"ties":[155],"robot-to-human":[156],"claims":[157],"evidence":[160],"bundle":[161],"combining":[162],"working":[163],"context":[164],"retrieved":[166],"outputs.":[168],"We":[169],"evaluate":[170],"JANUS":[171],"module-level":[173],"unit":[174],"tests":[175],"dietary":[178],"assistance":[179,211],"domain":[180],"grounded":[181],"on":[182],"knowledge":[184],"graph,":[185],"reporting":[186],"high":[187],"agreement":[188],"curated":[190],"references":[191],"practical":[193],"latency":[194],"profiles.":[195],"These":[196],"results":[197],"support":[198],"reasoning":[200],"promising":[203],"path":[204],"scalable,":[206],"auditable,":[207],"evidence-grounded":[209],"over":[212],"extended":[213],"horizons.":[215]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-02-04T00:00:00"}
