{"id":"https://openalex.org/W7103380445","doi":"https://doi.org/10.48550/arxiv.2311.00262","title":"Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents","display_name":"Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents","publication_year":2023,"publication_date":"2023-11-01","ids":{"openalex":"https://openalex.org/W7103380445","doi":"https://doi.org/10.48550/arxiv.2311.00262"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2311.00262","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00262","pdf_url":"https://arxiv.org/pdf/2311.00262","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":"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/2311.00262","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Deng, Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Deng, Yang","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhang, Wenxuan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Wenxuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Lam, Wai","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lam, Wai","raw_affiliation_strings":["The Chinese University of Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ng, See-Kiong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ng, See-Kiong","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":null,"display_name":"Chua, Tat-Seng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chua, Tat-Seng","raw_affiliation_strings":["National University of Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":3,"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":true,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9994999766349792,"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":0.9994999766349792,"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/T11902","display_name":"Intelligent Tutoring Systems and Adaptive Learning","score":9.999999747378752e-05,"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/T12128","display_name":"AI in Service Interactions","score":0.0,"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/proactive-dialogue","display_name":"proactive dialogue","score":0.9240000247955322},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.9330000281333923},{"id":"https://openalex.org/keywords/ai-feedback","display_name":"AI-generated feedback","score":0.4869999885559082},{"id":"https://openalex.org/keywords/reinforcement-learning-from-ai-feedback","display_name":"reinforcement learning from AI feedback","score":0.6769999861717224},{"id":"https://openalex.org/keywords/supervised-fine-tuning","display_name":"supervised fine-tuning","score":0.8529999852180481},{"id":"https://openalex.org/keywords/negotiation-dialogue","display_name":"negotiation dialogue","score":0.8460000157356262},{"id":"https://openalex.org/keywords/tutoring-dialogue","display_name":"tutoring dialogue","score":0.9879999756813049}],"concepts":[{"id":"https://openalex.org/C142944206","wikidata":"https://www.wikidata.org/wiki/Q1786137","display_name":"Proactivity","level":2,"score":0.8804000020027161},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.8255000114440918},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6886000037193298},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5913000106811523},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5436999797821045},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46230000257492065},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.3716999888420105},{"id":"https://openalex.org/C56739046","wikidata":"https://www.wikidata.org/wiki/Q192060","display_name":"Knowledge management","level":1,"score":0.36970001459121704},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.36070001125335693},{"id":"https://openalex.org/C2781281093","wikidata":"https://www.wikidata.org/wiki/Q329499","display_name":"Language planning","level":2,"score":0.34790000319480896},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.3330000042915344},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.32829999923706055},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.30889999866485596},{"id":"https://openalex.org/C195094911","wikidata":"https://www.wikidata.org/wiki/Q14167904","display_name":"Process management","level":1,"score":0.2881999909877777},{"id":"https://openalex.org/C114073186","wikidata":"https://www.wikidata.org/wiki/Q2631895","display_name":"Automated planning and scheduling","level":2,"score":0.2750000059604645},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.263700008392334}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2311.00262","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00262","pdf_url":"https://arxiv.org/pdf/2311.00262","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:ink.library.smu.edu.sg:sis_research-10118","doi":null,"is_oa":true,"landing_page_url":"https://ink.library.smu.edu.sg/sis_research/9115","pdf_url":null,"source":{"id":"https://openalex.org/S4306401925","display_name":"Singapore Management University Institutional Knowledge (InK) (Singapore Management University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I79891267","host_organization_name":"Singapore Management University","host_organization_lineage":["https://openalex.org/I79891267"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://openreview.net/forum?id=MCNqgUFTHI","raw_type":"Conference Proceeding Article"},{"id":"doi:10.48550/arxiv.2311.00262","doi":"https://doi.org/10.48550/arxiv.2311.00262","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2311.00262","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:2311.00262","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2311.00262","pdf_url":"https://arxiv.org/pdf/2311.00262","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6574276969","display_name":null,"funder_award_id":"I21001E0002","funder_id":"https://openalex.org/F4320307791","funder_display_name":"Cisco Systems"},{"id":"https://openalex.org/G700280992","display_name":null,"funder_award_id":"I21001E0002","funder_id":"https://openalex.org/F4320320698","funder_display_name":"National University of Singapore"}],"funders":[{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"},{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320698","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7103380445.pdf","grobid_xml":"https://content.openalex.org/works/W7103380445.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402671642","https://openalex.org/W4409363346","https://openalex.org/W7138169484","https://openalex.org/W4414429882","https://openalex.org/W7162283288","https://openalex.org/W4416268536","https://openalex.org/W4416034397","https://openalex.org/W7139044169","https://openalex.org/W7138261913","https://openalex.org/W4406461668"],"abstract_inverted_index":{"Proactive":[0],"dialogues":[1],"serve":[2],"as":[3,107,130,132],"a":[4,88,102,108,118],"practical":[5],"yet":[6],"challenging":[7],"dialogue":[8,20,37,90,99,110,154,191,212],"problem":[9],"in":[10,51],"the":[11,19,24,28,36,53,67,72,145,152,165,177,186,194],"era":[12],"of":[13,30,40,71,190],"large":[14],"language":[15,104],"models":[16],"(LLMs),":[17],"where":[18],"policy":[21,38,68,91,111,187],"planning":[22,39,69,92,188],"is":[23],"key":[25],"to":[26,77,80,94,122,161,171,184],"improving":[27],"proactivity":[29],"LLMs.":[31],"Most":[32],"existing":[33,206],"studies":[34],"enable":[35],"LLMs":[41,74,96],"using":[42],"various":[43],"prompting":[44],"schemes":[45],"or":[46,75],"iteratively":[47],"enhance":[48],"this":[49,84,150],"capability":[50,70,189],"handling":[52],"given":[54],"case":[55],"with":[56,101,139],"verbal":[57],"AI":[58,137],"feedback.":[59],"However,":[60],"these":[61],"approaches":[62,207],"are":[63],"either":[64],"bounded":[65],"by":[66,144,174],"frozen":[73],"hard":[76],"be":[78,159,169],"transferred":[79],"new":[81,89],"cases.":[82],"In":[83,149,180],"work,":[85],"we":[86,116,182],"introduce":[87],"paradigm":[93],"strategize":[95],"for":[97],"proactive":[98,211],"problems":[100],"tunable":[103],"model":[105],"plug-in":[106],"plug-and-play":[109],"planner,":[112],"named":[113],"PPDPP.":[114],"Specifically,":[115],"develop":[117],"novel":[119],"training":[120],"framework":[121],"facilitate":[123],"supervised":[124],"fine-tuning":[125],"over":[126],"available":[127],"human-annotated":[128],"data":[129,142],"well":[131],"reinforcement":[133],"learning":[134],"from":[135],"goal-oriented":[136],"feedback":[138],"dynamic":[140],"interaction":[141],"collected":[143],"LLM-based":[146],"self-play":[147],"simulation.":[148],"manner,":[151],"LLM-powered":[153],"agent":[155],"can":[156],"not":[157],"only":[158],"generalized":[160],"different":[162,172,210],"cases":[163],"after":[164],"training,":[166],"but":[167],"also":[168],"applicable":[170],"applications":[173],"just":[175],"substituting":[176],"learned":[178],"plug-in.":[179],"addition,":[181],"propose":[183],"evaluate":[185],"systems":[192],"under":[193],"interactive":[195],"setting.":[196],"Experimental":[197],"results":[198],"demonstrate":[199],"that":[200],"PPDPP":[201],"consistently":[202],"and":[203,218],"substantially":[204],"outperforms":[205],"on":[208],"three":[209],"applications,":[213],"including":[214],"negotiation,":[215],"emotional":[216],"support,":[217],"tutoring":[219],"dialogues.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2025-10-10T00:00:00"}