{"id":"https://openalex.org/W7138261913","doi":"https://doi.org/10.1609/aaai.v40i36.40244","title":"DialogXpert: Driving Intelligent and Emotion-Aware Conversations Through Online Value-Based Reinforcement Learning with LLM Priors","display_name":"DialogXpert: Driving Intelligent and Emotion-Aware Conversations Through Online Value-Based Reinforcement Learning with LLM Priors","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138261913","doi":"https://doi.org/10.1609/aaai.v40i36.40244"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v40i36.40244","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40244","pdf_url":null,"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":null,"license_id":null,"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://doi.org/10.1609/aaai.v40i36.40244","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058658707","display_name":"Tazeek Bin Abdur Rakib","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tazeek Bin Abdur Rakib","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065572305","display_name":"Ambuj Mehrish","orcid":"https://orcid.org/0000-0003-4240-9915"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ambuj Mehrish","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069570912","display_name":"Lay-Ki Soon","orcid":"https://orcid.org/0000-0002-8072-242X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lay-Ki Soon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129747575","display_name":"Wern Han Lim","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wern Han Lim","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129715744","display_name":"Soujanya Poria","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Soujanya Poria","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.53988604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"36","first_page":"29967","last_page":"29975"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.46959999203681946,"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"}},"topics":[{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.46959999203681946,"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"}},{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.16840000450611115,"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":0.10920000076293945,"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/task","display_name":"Task (project management)","score":0.6705999970436096},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6488999724388123},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6366000175476074},{"id":"https://openalex.org/keywords/negotiation","display_name":"Negotiation","score":0.6004999876022339},{"id":"https://openalex.org/keywords/prior-probability","display_name":"Prior probability","score":0.5539000034332275},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.3734000027179718},{"id":"https://openalex.org/keywords/tracking","display_name":"Tracking (education)","score":0.3483000099658966}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6809999942779541},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6705999970436096},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6488999724388123},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6366000175476074},{"id":"https://openalex.org/C199776023","wikidata":"https://www.wikidata.org/wiki/Q202875","display_name":"Negotiation","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.5539000034332275},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5246999859809875},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4399000108242035},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.3734000027179718},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.3352999985218048},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.33160001039505005},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.3206000030040741},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31279999017715454},{"id":"https://openalex.org/C2776352735","wikidata":"https://www.wikidata.org/wiki/Q2313343","display_name":"Turn-taking","level":3,"score":0.3000999987125397},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.29350000619888306},{"id":"https://openalex.org/C2777200299","wikidata":"https://www.wikidata.org/wiki/Q52943","display_name":"Conversation","level":2,"score":0.28349998593330383},{"id":"https://openalex.org/C49774154","wikidata":"https://www.wikidata.org/wiki/Q131765","display_name":"Multimedia","level":1,"score":0.2721000015735626},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.26660001277923584},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1609/aaai.v40i36.40244","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40244","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:ojs.aaai.org:article/40244","is_oa":false,"landing_page_url":"https://ojs.aaai.org/index.php/AAAI/article/view/40244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2159-5399","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i36.40244","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i36.40244","pdf_url":null,"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":null,"license_id":null,"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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.5717304944992065}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320320709","display_name":"National Research Foundation Singapore","ror":"https://ror.org/03cpyc314"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Large-language-model":[0],"(LLM)":[1],"agents":[2],"excel":[3],"at":[4,123],"reactive":[5],"dialogue":[6,121],"but":[7],"struggle":[8],"with":[9,93,99],"proactive,":[10],"goal-driven":[11],"interactions":[12],"due":[13],"to":[14,28,52,69,89],"myopic":[15],"decoding":[16],"and":[17,39,83,118],"costly":[18],"planning.":[19],"We":[20],"introduce":[21],"DialogXpert,":[22],"which":[23],"leverages":[24],"a":[25,30,41,75,100],"frozen":[26],"LLM":[27,102],"propose":[29],"small,":[31],"high-quality":[32],"set":[33],"of":[34],"candidate":[35],"actions":[36],"per":[37],"turn":[38],"employs":[40],"compact":[42],"Q-network":[43],"over":[44],"fixed":[45],"BERT":[46],"embeddings":[47],"trained":[48],"via":[49],"temporal-difference":[50],"learning":[51],"select":[53],"optimal":[54],"moves":[55],"within":[56],"this":[57],"reduced":[58],"space.":[59],"By":[60],"tracking":[61],"the":[62,71],"user's":[63],"emotions":[64],"DialogXpert":[65,86],"tailors":[66],"each":[67],"decision":[68],"advance":[70],"task":[72],"while":[73,108],"nurturing":[74],"genuine,":[76],"empathetic":[77],"connection.":[78],"Across":[79],"negotiation,":[80],"emotional":[81],"support,":[82],"tutoring":[84],"benchmarks,":[85],"drives":[87],"conversations":[88],"under":[90],"3":[91],"turns":[92],"success":[94,105],"rates":[95],"exceeding":[96],"94%":[97],"and,":[98],"larger":[101],"prior,":[103],"pushes":[104],"above":[106],"97%":[107],"markedly":[109],"improving":[110],"negotiation":[111],"outcomes.":[112],"This":[113],"framework":[114],"delivers":[115],"real-time,":[116],"strategic,":[117],"emotionally":[119],"intelligent":[120],"planning":[122],"scale.":[124]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-18T00:00:00"}