{"id":"https://openalex.org/W7138169484","doi":"https://doi.org/10.1609/aaai.v40i39.40638","title":"A General Highly Accurate Online Planning Method Integrating Large Language Models into Nested Rollout Policy Adaptation for Dialogue Tasks","display_name":"A General Highly Accurate Online Planning Method Integrating Large Language Models into Nested Rollout Policy Adaptation for Dialogue Tasks","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138169484","doi":"https://doi.org/10.1609/aaai.v40i39.40638"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i39.40638","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40638","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40638/44599","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40638/44599","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129674718","display_name":"Hui Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Hui Wang","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University\nAnhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University\nAnhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042522512","display_name":"Fafa Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fafa Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University\nAnhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University\nAnhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129687557","display_name":"Xiaoyu Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoyu Zhang","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University\nAnhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University\nAnhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129727999","display_name":"Chaoxu Mu","orcid":null},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoxu Mu","raw_affiliation_strings":["School of Artificial Intelligence, Anhui University\nAnhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University\nPengcheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Anhui University\nAnhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University\nPengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5129674718"],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.38543897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"39","first_page":"33503","last_page":"33511"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.3912999927997589,"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":0.3912999927997589,"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/T10028","display_name":"Topic Modeling","score":0.15629999339580536,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.1256999969482422,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7394999861717224},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.5782999992370605},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.3747999966144562},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.33649998903274536},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.3246000111103058},{"id":"https://openalex.org/keywords/human-behavior","display_name":"Human behavior","score":0.2775999903678894}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7839999794960022},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7394999861717224},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4300000071525574},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3747999966144562},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36469998955726624},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.33649998903274536},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3246000111103058},{"id":"https://openalex.org/C117035363","wikidata":"https://www.wikidata.org/wiki/Q3769299","display_name":"Human behavior","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C123587114","wikidata":"https://www.wikidata.org/wiki/Q2101508","display_name":"Policy analysis","level":2,"score":0.27480000257492065},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.26809999346733093},{"id":"https://openalex.org/C67712803","wikidata":"https://www.wikidata.org/wiki/Q7901853","display_name":"User modeling","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C539667460","wikidata":"https://www.wikidata.org/wiki/Q2414942","display_name":"Management science","level":1,"score":0.25699999928474426},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i39.40638","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40638","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40638/44599","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i39.40638","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i39.40638","pdf_url":"https://ojs.aaai.org/index.php/AAAI/article/download/40638/44599","source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7138169484.pdf","grobid_xml":"https://content.openalex.org/works/W7138169484.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"In":[0],"goal-oriented":[1,141],"dialogue":[2,54,76,112,133,142],"tasks,":[3],"the":[4,10,101,132,175],"main":[5],"challenge":[6],"is":[7,32],"to":[8,50,52,58,93,127,185],"steer":[9],"interaction":[11],"towards":[12],"a":[13,17,74,88,107,167],"given":[14],"goal":[15],"within":[16],"limited":[18],"number":[19],"of":[20,96,119,179],"turns.":[21],"Existing":[22],"approaches":[23],"either":[24],"rely":[25],"on":[26,35,138,183],"elaborate":[27],"prompt":[28,150],"engineering,":[29],"whose":[30],"effectiveness":[31],"heavily":[33],"dependent":[34],"human":[36],"experience,":[37],"or":[38],"integrate":[39],"policy":[40,44,77,125,163],"networks":[41],"and":[42,56,98,114,124,152,161,177],"pre-trained":[43,154,162],"models,":[45],"which":[46],"are":[47],"usually":[48],"difficult":[49],"adapt":[51],"new":[53],"scenarios":[55],"costly":[57],"train.":[59],"Therefore,":[60],"in":[61],"this":[62],"paper,":[63],"we":[64],"present":[65],"Nested":[66],"Rollout":[67],"Policy":[68],"Adaptation":[69],"for":[70,111],"Goal-oriented":[71],"Dialogue":[72],"(NRPA-GD),":[73],"novel":[75],"planning":[78,181,188],"method":[79],"that":[80,145],"completely":[81],"avoids":[82],"specific":[83],"model":[84],"training":[85],"by":[86],"utilizing":[87],"Large":[89],"Language":[90],"Model":[91],"(LLM)":[92],"simulate":[94],"behaviors":[95],"user":[97],"system":[99],"at":[100],"same":[102],"time.":[103],"Specifically,":[104],"NRPA-GD":[105,146,158],"constructs":[106],"complete":[108],"evaluation":[109],"mechanism":[110],"trajectories":[113],"employs":[115],"an":[116],"optimization":[117],"framework":[118],"nested":[120],"Monte":[121],"Carlo":[122],"simulation":[123],"self-adaptation":[126],"dynamically":[128],"adjust":[129],"policies":[130],"during":[131],"process.":[134],"The":[135,170],"experimental":[136],"results":[137],"four":[139],"typical":[140],"datasets":[143],"show":[144],"outperforms":[147],"both":[148],"existing":[149],"engineering":[151],"specifically":[153],"model-based":[155],"methods.":[156],"Impressively,":[157],"surpasses":[159],"ChatGPT":[160],"models":[164],"with":[165],"only":[166],"0.6-billion-parameter":[168],"LLM.":[169],"proposed":[171],"approach":[172],"further":[173],"demonstrates":[174],"advantages":[176],"novelty":[178],"employing":[180],"methods":[182],"LLMs":[184],"solve":[186],"practical":[187],"tasks.":[189]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}