{"id":"https://openalex.org/W4396757501","doi":"https://doi.org/10.1145/3589334.3645365","title":"Multimodal Query Suggestion with Multi-Agent Reinforcement Learning from Human Feedback","display_name":"Multimodal Query Suggestion with Multi-Agent Reinforcement Learning from Human Feedback","publication_year":2024,"publication_date":"2024-05-08","ids":{"openalex":"https://openalex.org/W4396757501","doi":"https://doi.org/10.1145/3589334.3645365"},"language":"en","primary_location":{"id":"doi:10.1145/3589334.3645365","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589334.3645365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100401111","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0002-7064-6267"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Huawei Singapore Research Center, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center, Singapore, Singapore","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5093895820","display_name":"Bingzheng Gan","orcid":"https://orcid.org/0009-0000-9930-6859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingzheng Gan","raw_affiliation_strings":["Huawei Singapore Research Center, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center, Singapore, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071266799","display_name":"Wei Shi","orcid":"https://orcid.org/0009-0006-2717-4192"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wei Shi","raw_affiliation_strings":["Huawei Singapore Research Center, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Huawei Singapore Research Center, Singapore, Singapore","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100401111"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5312,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.9033361,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1374","last_page":"1385"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12031","display_name":"Speech and dialogue systems","score":0.9782000184059143,"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":0.9782000184059143,"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":0.9729999899864197,"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/T10320","display_name":"Neural Networks and Applications","score":0.9628999829292297,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8305785655975342},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.769751250743866},{"id":"https://openalex.org/keywords/error-driven-learning","display_name":"Error-driven learning","score":0.4692651629447937},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4450652301311493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.44241228699684143},{"id":"https://openalex.org/keywords/query-expansion","display_name":"Query expansion","score":0.4105827212333679},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32774752378463745},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.31635093688964844}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8305785655975342},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.769751250743866},{"id":"https://openalex.org/C47932503","wikidata":"https://www.wikidata.org/wiki/Q5395689","display_name":"Error-driven learning","level":3,"score":0.4692651629447937},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4450652301311493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.44241228699684143},{"id":"https://openalex.org/C99016210","wikidata":"https://www.wikidata.org/wiki/Q5488129","display_name":"Query expansion","level":2,"score":0.4105827212333679},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32774752378463745},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.31635093688964844}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3589334.3645365","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3589334.3645365","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM Web Conference 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1966043174","https://openalex.org/W1970956440","https://openalex.org/W1993692165","https://openalex.org/W2005679862","https://openalex.org/W2007105673","https://openalex.org/W2030939582","https://openalex.org/W2062879799","https://openalex.org/W2093245971","https://openalex.org/W2152433756","https://openalex.org/W2155505106","https://openalex.org/W2164986850","https://openalex.org/W2741195357","https://openalex.org/W2765293359","https://openalex.org/W3172750682","https://openalex.org/W3184735396","https://openalex.org/W4226278401","https://openalex.org/W4251560691","https://openalex.org/W4292779060","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2371091044","https://openalex.org/W2171010636","https://openalex.org/W87513465","https://openalex.org/W1966803121","https://openalex.org/W2391666574","https://openalex.org/W2786230833","https://openalex.org/W3203256658","https://openalex.org/W2352650970","https://openalex.org/W1544514152","https://openalex.org/W1493952344"],"abstract_inverted_index":{"In":[0,56],"the":[1,81,90,94,110,118,128,133],"rapidly":[2],"evolving":[3],"landscape":[4],"of":[5,85,96,120],"information":[6,161],"retrieval,":[7],"search":[8,51,86,140],"engines":[9],"strive":[10],"to":[11,18,70,79,108,127],"provide":[12],"more":[13],"personalized":[14],"and":[15,83,154],"relevant":[16],"results":[17],"users.":[19],"Query":[20,64],"suggestion":[21,41,152],"systems":[22,42,153],"play":[23],"a":[24,61,123,156],"crucial":[25],"role":[26],"in":[27,34],"achieving":[28],"this":[29,57],"goal":[30],"by":[31],"assisting":[32],"users":[33],"formulating":[35],"effective":[36],"queries.":[37],"However,":[38],"existing":[39,130],"query":[40,72,77,151],"mainly":[43],"rely":[44],"on":[45,75,159],"textual":[46],"inputs,":[47],"potentially":[48],"limiting":[49],"user":[50,76,146],"experiences":[52],"for":[53],"querying":[54],"images.":[55],"paper,":[58],"we":[59,116],"introduce":[60],"novel":[62],"Multimodal":[63],"Suggestion":[65],"(MMQS)":[66],"task,":[67],"which":[68,143],"aims":[69],"generate":[71],"suggestions":[73],"based":[74],"images":[78],"improve":[80],"intentionality":[82],"diversity":[84],"results.":[87],"We":[88],"present":[89],"RL4Sugg":[91],"framework,":[92],"leveraging":[93],"power":[95],"Large":[97],"Language":[98],"Models":[99],"(LLMs)":[100],"with":[101],"Multi-Agent":[102],"Reinforcement":[103],"Learning":[104],"from":[105],"Human":[106],"Feedback":[107],"optimize":[109],"generation":[111],"process.":[112],"Through":[113],"comprehensive":[114],"experiments,":[115],"validate":[117],"effectiveness":[119],"RL4Sugg,":[121],"demonstrating":[122],"18%":[124],"improvement":[125],"compared":[126],"best":[129],"approach.":[131],"Moreover,":[132],"MMQS":[134],"has":[135],"been":[136],"transferred":[137],"into":[138],"real-world":[139],"engine":[141],"products,":[142],"yield":[144],"enhanced":[145],"engagement.":[147],"Our":[148],"research":[149],"advances":[150],"provides":[155],"new":[157],"perspective":[158],"multimodal":[160],"retrieval.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2}],"updated_date":"2026-03-12T08:34:05.389933","created_date":"2025-10-10T00:00:00"}