{"id":"https://openalex.org/W7152439051","doi":"https://doi.org/10.1145/3774904.3792129","title":"DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs","display_name":"DARA: Few-shot Budget Allocation in Online Advertising via In-Context Decision Making with RL-Finetuned LLMs","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7152439051","doi":"https://doi.org/10.1145/3774904.3792129"},"language":null,"primary_location":{"id":"doi:10.1145/3774904.3792129","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792129","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3774904.3792129","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123594671","display_name":"Mingxuan Song","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingxuan Song","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6319-4290","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102722801","display_name":"Yusen Huo","orcid":"https://orcid.org/0009-0006-8863-3209"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yusen Huo","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0006-8863-3209","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bohan Zhou","orcid":"https://orcid.org/0000-0001-5495-7631"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bohan Zhou","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5495-7631","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123577951","display_name":"Shenglin Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shenglin Yin","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5216-9946","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102979232","display_name":"Zhen Xiao","orcid":"https://orcid.org/0000-0002-6784-9709"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Xiao","raw_affiliation_strings":["School of Computer Science, Peking University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6784-9709","affiliations":[{"raw_affiliation_string":"School of Computer Science, Peking University, Beijing, China","institution_ids":["https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123556408","display_name":"Jieyi Long","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116807","display_name":"QED Labs","ror":"https://ror.org/023bn8s91","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210116807"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jieyi Long","raw_affiliation_strings":["Theta Labs, Inc., San Jose, CA, USA"],"raw_orcid":"https://orcid.org/0009-0007-4646-7131","affiliations":[{"raw_affiliation_string":"Theta Labs, Inc., San Jose, CA, USA","institution_ids":["https://openalex.org/I4210116807"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhilin Zhang","orcid":"https://orcid.org/0000-0002-4251-8575"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhilin Zhang","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4251-8575","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059373349","display_name":"Chuan Yu","orcid":"https://orcid.org/0000-0001-8094-1545"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chuan Yu","raw_affiliation_strings":["Alibaba Group, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-8094-1545","affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, China","institution_ids":["https://openalex.org/I45928872"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"40","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12101","display_name":"Advanced Bandit Algorithms Research","score":0.13300000131130219,"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":0.13300000131130219,"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/T10203","display_name":"Recommender Systems and Techniques","score":0.11029999703168869,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11596","display_name":"Constraint Satisfaction and Optimization","score":0.09319999814033508,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/online-advertising","display_name":"Online advertising","score":0.3628000020980835},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.31520000100135803},{"id":"https://openalex.org/keywords/budget-constraint","display_name":"Budget constraint","score":0.2921000123023987},{"id":"https://openalex.org/keywords/advertising-campaign","display_name":"Advertising campaign","score":0.2838999927043915}],"concepts":[{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.6029999852180481},{"id":"https://openalex.org/C112698675","wikidata":"https://www.wikidata.org/wiki/Q37038","display_name":"Advertising","level":1,"score":0.5630000233650208},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.42809998989105225},{"id":"https://openalex.org/C512338625","wikidata":"https://www.wikidata.org/wiki/Q624902","display_name":"Online advertising","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.31520000100135803},{"id":"https://openalex.org/C39549134","wikidata":"https://www.wikidata.org/wiki/Q133080","display_name":"Public relations","level":1,"score":0.30140000581741333},{"id":"https://openalex.org/C8505890","wikidata":"https://www.wikidata.org/wiki/Q605095","display_name":"Budget constraint","level":2,"score":0.2921000123023987},{"id":"https://openalex.org/C110350745","wikidata":"https://www.wikidata.org/wiki/Q1761818","display_name":"Advertising campaign","level":2,"score":0.2838999927043915},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.2809999883174896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.27309998869895935},{"id":"https://openalex.org/C108827166","wikidata":"https://www.wikidata.org/wiki/Q175975","display_name":"Internet privacy","level":1,"score":0.2728999853134155}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3774904.3792129","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792129","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3774904.3792129","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3774904.3792129","pdf_url":null,"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 ACM Web Conference 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.6786013245582581,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1995045726","https://openalex.org/W2117340018","https://openalex.org/W2767050701","https://openalex.org/W3004257040","https://openalex.org/W3010048053","https://openalex.org/W3027406032","https://openalex.org/W3154055679","https://openalex.org/W3160638507","https://openalex.org/W4280496608","https://openalex.org/W4389723380","https://openalex.org/W4396736348","https://openalex.org/W4396758667","https://openalex.org/W4401863338","https://openalex.org/W4407449715","https://openalex.org/W4410088778","https://openalex.org/W4410088823"],"related_works":[],"abstract_inverted_index":{"Optimizing":[0],"the":[1,19,73,102,121],"advertiser's":[2],"cumulative":[3,185],"value":[4,187],"of":[5,21,184],"winning":[6],"impressions":[7],"under":[8,18,188],"budget":[9,189],"constraints":[10],"poses":[11],"a":[12,54,115,127,138],"complex":[13],"challenge":[14],"in":[15,36,182],"online":[16],"advertising,":[17],"paradigm":[20],"AI-Generated":[22],"Bidding":[23],"(AIGB).":[24],"Advertisers":[25],"often":[26],"have":[27],"personalized":[28],"objectives":[29],"but":[30],"limited":[31,68],"historical":[32],"interaction":[33],"data,":[34],"resulting":[35],"few-shot":[37,128],"scenarios":[38],"where":[39],"traditional":[40],"reinforcement":[41],"learning":[42,63,156],"(RL)":[43],"methods":[44],"struggle":[45],"to":[46,65,152],"perform":[47],"effectively.":[48],"Large":[49],"Language":[50],"Models":[51],"(LLMs)":[52],"offer":[53],"promising":[55],"alternative":[56],"for":[57,77],"AIGB":[58,163],"by":[59,99,162],"leveraging":[60],"their":[61],"in-context":[62,135,155],"capabilities":[64],"generalize":[66],"from":[67],"data.":[69],"However,":[70],"they":[71],"lack":[72],"numerical":[74,97],"precision":[75,98],"required":[76,161],"fine-grained":[78,139],"optimization.":[79],"To":[80],"address":[81],"this":[82,109],"limitation,":[83],"we":[84,111],"introduce":[85],"GRPO-Adaptive,":[86],"an":[87],"efficient":[88],"LLM":[89],"post-training":[90],"strategy":[91],"that":[92,119,130,141,175],"enhances":[93],"both":[94,168],"reasoning":[95],"and":[96,137,170],"dynamically":[100],"updating":[101],"reference":[103],"policy":[104],"during":[105],"training.":[106],"Built":[107],"upon":[108],"foundation,":[110],"further":[112],"propose":[113],"DARA,":[114],"novel":[116],"dual-phase":[117],"framework":[118],"decomposes":[120],"decision-making":[122],"process":[123],"into":[124],"two":[125],"stages:":[126],"reasoner":[129],"generates":[131],"initial":[132],"plans":[133,144],"via":[134],"prompting,":[136],"optimizer":[140],"refines":[142],"these":[143],"using":[145],"feedback-driven":[146],"reasoning.":[147],"This":[148],"separation":[149],"allows":[150],"DARA":[151],"combine":[153],"LLMs'":[154],"strengths":[157],"with":[158],"precise":[159],"adaptability":[160],"tasks.":[164],"Extensive":[165],"experiments":[166],"on":[167],"real-world":[169],"synthetic":[171],"data":[172],"environments":[173],"demonstrate":[174],"our":[176],"approach":[177],"consistently":[178],"outperforms":[179],"existing":[180],"baselines":[181],"terms":[183],"advertiser":[186],"constraints.":[190]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-04-10T00:00:00"}