{"id":"https://openalex.org/W7166853735","doi":"https://doi.org/10.18653/v1/2026.acl-long.2180","title":"DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual Systems","display_name":"DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual Systems","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7166853735","doi":"https://doi.org/10.18653/v1/2026.acl-long.2180"},"language":null,"primary_location":{"id":"doi:10.18653/v1/2026.acl-long.2180","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2180","pdf_url":"https://aclanthology.org/2026.acl-long.2180.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2026.acl-long.2180.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139801220","display_name":"Shuyu Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shuyu Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101516851","display_name":"Yifan Wei","orcid":"https://orcid.org/0000-0003-2956-534X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yifan Wei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107900566","display_name":"Jialuo Yuan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jialuo Yuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139732553","display_name":"Xinru Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinru Wang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139839096","display_name":"Yanmin Zhu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yanmin Zhu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139829625","display_name":"Yujie Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yujie Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139832719","display_name":"Bin Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin Li","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":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.87012987,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"47079","last_page":"47111"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.30880001187324524,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.30880001187324524,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.14380000531673431,"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/T12031","display_name":"Speech and dialogue systems","score":0.08609999716281891,"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/dual","display_name":"Dual (grammatical number)","score":0.5299999713897705},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.4674000144004822},{"id":"https://openalex.org/keywords/balance","display_name":"Balance (ability)","score":0.4099999964237213},{"id":"https://openalex.org/keywords/dialog-box","display_name":"Dialog box","score":0.3409000039100647},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.3021000027656555},{"id":"https://openalex.org/keywords/cognitive-systems","display_name":"Cognitive systems","score":0.298799991607666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6614999771118164},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.5299999713897705},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C168031717","wikidata":"https://www.wikidata.org/wiki/Q1530280","display_name":"Balance (ability)","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C173853756","wikidata":"https://www.wikidata.org/wiki/Q86915","display_name":"Dialog box","level":2,"score":0.3409000039100647},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3384000062942505},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3021000027656555},{"id":"https://openalex.org/C2986342778","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Cognitive systems","level":3,"score":0.298799991607666},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.29660001397132874},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2745000123977661},{"id":"https://openalex.org/C92298750","wikidata":"https://www.wikidata.org/wiki/Q17008161","display_name":"Cognitive computing","level":3,"score":0.2624000012874603},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2612999975681305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2026.acl-long.2180","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2180","pdf_url":"https://aclanthology.org/2026.acl-long.2180.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2026.acl-long.2180","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2026.acl-long.2180","pdf_url":"https://aclanthology.org/2026.acl-long.2180.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1081045896","display_name":null,"funder_award_id":"62472277","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3242927586","display_name":null,"funder_award_id":"CJGJZD20230724093303007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4838640859","display_name":null,"funder_award_id":"KJZD20240903101259001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6364853269","display_name":null,"funder_award_id":"D2404001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336405","display_name":"Special Project for Research and Development in Key areas of Guangdong Province","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7166853735.pdf","grobid_xml":"https://content.openalex.org/works/W7166853735.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Task":[0],"oriented":[1],"dialog":[2,16,31,49],"systems":[3],"often":[4],"rely":[5],"on":[6,78,86],"static":[7],"exploration":[8,21,38],"strategies":[9],"that":[10,35,47,60,91,106],"do":[11],"not":[12],"adapt":[13],"to":[14,19],"dynamic":[15],"contexts,":[17],"leading":[18],"inefficient":[20],"and":[22,53,70,82,100],"suboptimal":[23],"performance.We":[24],"propose":[25],"DyBBT":[26,92],"1":[27],",":[28],"a":[29,41,57,64,71],"novel":[30],"policy":[32],"learning":[33],"framework":[34],"formalizes":[36],"the":[37],"challenge":[39],"through":[40],"structured":[42],"cognitive":[43,80],"state":[44],"space":[45],"C":[46],"captures":[48],"progression,":[50],"user":[51],"uncertainty,":[52],"slot":[54],"dependency.DyBBT":[55],"proposes":[56],"bandit-inspired":[58],"meta-controller":[59],"dynamically":[61],"switches":[62],"between":[63],"fast":[65],"intuitive":[66],"inference":[67],"(System":[68,75],"1)":[69],"slow":[72],"deliberative":[73],"reasoner":[74],"2)":[76],"based":[77],"real-time":[79],"states":[81],"visitation":[83],"counts.Extensive":[84],"experiments":[85],"single-and":[87],"multi-domain":[88],"benchmarks":[89],"show":[90],"achieves":[93],"SOTA":[94],"performance":[95],"in":[96],"success":[97],"rate,":[98],"efficiency,":[99],"generalization,":[101],"with":[102,111],"human":[103],"evaluations":[104],"confirming":[105],"its":[107],"decisions":[108],"are":[109],"well-aligned":[110],"expert":[112],"judgment.":[113]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-07-02T00:00:00"}
