{"id":"https://openalex.org/W7130562987","doi":"https://doi.org/10.48550/arxiv.2602.16173","title":"Learning Personalized Agents from Human Feedback","display_name":"Learning Personalized Agents from Human Feedback","publication_year":2026,"publication_date":"2026-02-18","ids":{"openalex":"https://openalex.org/W7130562987","doi":"https://doi.org/10.48550/arxiv.2602.16173"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2602.16173","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.16173","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,"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"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2602.16173","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5126373595","display_name":"Kaiqu Liang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liang, Kaiqu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126365239","display_name":"Julia Kruk","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kruk, Julia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030632256","display_name":"Shengyi Qian","orcid":"https://orcid.org/0000-0003-0262-2412"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qian, Shengyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113823432","display_name":"Xianjun Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Xianjun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126430042","display_name":"Shengjie Bi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bi, Shengjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014146843","display_name":"Yuanshun Yao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yao, Yuanshun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114634597","display_name":"Shaoliang Nie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Shaoliang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126386372","display_name":"Mingyang Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Mingyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072741893","display_name":"Lijuan Liu","orcid":"https://orcid.org/0000-0002-1456-5163"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Lijuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126361097","display_name":"Jaime Fern\u00e1ndez Fisac","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fisac, Jaime Fern\u00e1ndez","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126434062","display_name":"Shuyan Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhou, Shuyan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5126378330","display_name":"Saghar Hosseini","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hosseini, Saghar","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":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/T10709","display_name":"Social Robot Interaction and HRI","score":0.3181000053882599,"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"}},"topics":[{"id":"https://openalex.org/T10709","display_name":"Social Robot Interaction and HRI","score":0.3181000053882599,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.07129999995231628,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11431","display_name":"Action Observation and Synchronization","score":0.05770000070333481,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.800599992275238},{"id":"https://openalex.org/keywords/preference","display_name":"Preference","score":0.5784000158309937},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5382000207901001},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.46320000290870667},{"id":"https://openalex.org/keywords/embodied-cognition","display_name":"Embodied cognition","score":0.4207000136375427},{"id":"https://openalex.org/keywords/preference-elicitation","display_name":"Preference elicitation","score":0.4043999910354614},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.39250001311302185},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.37959998846054077},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.3434000015258789}],"concepts":[{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.800599992275238},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562000155448914},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.6069999933242798},{"id":"https://openalex.org/C2781249084","wikidata":"https://www.wikidata.org/wiki/Q908656","display_name":"Preference","level":2,"score":0.5784000158309937},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5382000207901001},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4368000030517578},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.4207000136375427},{"id":"https://openalex.org/C2777868144","wikidata":"https://www.wikidata.org/wiki/Q7239817","display_name":"Preference elicitation","level":3,"score":0.4043999910354614},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.39250001311302185},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.37959998846054077},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.337799996137619},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3231000006198883},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31310001015663147},{"id":"https://openalex.org/C2781235140","wikidata":"https://www.wikidata.org/wiki/Q275131","display_name":"Scratch","level":2,"score":0.2994999885559082},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.29490000009536743},{"id":"https://openalex.org/C557471498","wikidata":"https://www.wikidata.org/wiki/Q554950","display_name":"Recommender system","level":2,"score":0.28760001063346863},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.28450000286102295},{"id":"https://openalex.org/C313442","wikidata":"https://www.wikidata.org/wiki/Q778556","display_name":"Persona","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C181204326","wikidata":"https://www.wikidata.org/wiki/Q7239820","display_name":"Preference learning","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C2986087404","wikidata":"https://www.wikidata.org/wiki/Q15946010","display_name":"Online learning","level":2,"score":0.2646999955177307},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2590999901294708},{"id":"https://openalex.org/C186886427","wikidata":"https://www.wikidata.org/wiki/Q5441213","display_name":"Feedback loop","level":2,"score":0.2540999948978424}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2602.16173","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.16173","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,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2602.16173","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.16173","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,"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"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Modern":[0],"AI":[1],"agents":[2,69],"are":[3],"powerful":[4],"but":[5],"often":[6],"fail":[7],"to":[8,88,104,134,143,183],"align":[9],"with":[10,44,48,157],"the":[11],"idiosyncratic,":[12],"evolving":[13],"preferences":[14,49,95,108,137],"of":[15],"individual":[16],"users.":[17],"Prior":[18],"approaches":[19,42],"typically":[20],"rely":[21],"on":[22,30],"static":[23],"datasets,":[24],"either":[25],"training":[26],"implicit":[27],"preference":[28,184],"models":[29],"interaction":[31,74],"history":[32],"or":[33],"encoding":[34],"user":[35],"profiles":[36],"in":[37,67,94,122],"external":[38],"memory.":[39,78],"However,":[40],"these":[41],"struggle":[43],"new":[45],"users":[46],"and":[47,99,119,125,140,149,167,172,179],"that":[50,153],"change":[51],"over":[52],"time.":[53],"We":[54],"introduce":[55],"Personalized":[56],"Agents":[57],"from":[58,72,97,138],"Human":[59],"Feedback":[60],"(PAHF),":[61],"a":[62,81,116],"framework":[63],"for":[64],"continual":[65],"personalization":[66,177],"which":[68],"learn":[70,135],"online":[71,126],"live":[73],"using":[75],"explicit":[76,155],"per-user":[77],"PAHF":[79,163],"operationalizes":[80],"three-step":[82],"loop:":[83],"(1)":[84],"seeking":[85],"pre-action":[86],"clarification":[87],"resolve":[89],"ambiguity,":[90],"(2)":[91],"grounding":[92],"actions":[93],"retrieved":[96],"memory,":[98],"(3)":[100],"integrating":[101,154],"post-action":[102],"feedback":[103,159],"update":[105],"memory":[106,156],"when":[107],"drift.":[109],"To":[110],"evaluate":[111],"this":[112],"capability,":[113],"we":[114],"develop":[115],"four-phase":[117],"protocol":[118],"two":[120],"benchmarks":[121,129],"embodied":[123],"manipulation":[124],"shopping.":[127],"These":[128],"quantify":[130],"an":[131],"agent's":[132],"ability":[133],"initial":[136,176],"scratch":[139],"subsequently":[141],"adapt":[142],"persona":[144],"shifts.":[145,185],"Our":[146],"theoretical":[147],"analysis":[148],"empirical":[150],"results":[151],"show":[152],"dual":[158],"channels":[160],"is":[161],"critical:":[162],"learns":[164],"substantially":[165],"faster":[166],"consistently":[168],"outperforms":[169],"both":[170],"no-memory":[171],"single-channel":[173],"baselines,":[174],"reducing":[175],"error":[178],"enabling":[180],"rapid":[181],"adaptation":[182]},"counts_by_year":[],"updated_date":"2026-08-16T07:02:28.622633","created_date":"2026-02-20T00:00:00"}