{"id":"https://openalex.org/W4414360215","doi":"https://doi.org/10.24963/ijcai.2025/994","title":"Reinforced In-Context Black-Box Optimization","display_name":"Reinforced In-Context Black-Box Optimization","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360215","doi":"https://doi.org/10.24963/ijcai.2025/994"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/994","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5100692130","display_name":"Lei Song","orcid":"https://orcid.org/0000-0001-5958-9321"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lei Song","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China","School of Artificial Intelligence, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105346359","display_name":"Chen-Xiao Gao","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chen-Xiao Gao","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China","School of Artificial Intelligence, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100751825","display_name":"Ke Xue","orcid":"https://orcid.org/0000-0001-5347-2712"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ke Xue","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China","School of Artificial Intelligence, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101660746","display_name":"Chenyang Wu","orcid":"https://orcid.org/0000-0003-0920-7895"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenyang Wu","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China","School of Artificial Intelligence, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407480","display_name":"Dong Li","orcid":"https://orcid.org/0000-0002-7527-5645"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong Li","raw_affiliation_strings":["Huawei Noah\u2019s Ark Lab, China"],"affiliations":[{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047509839","display_name":"Jianye Hao","orcid":"https://orcid.org/0000-0002-0422-8235"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]},{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianye Hao","raw_affiliation_strings":["College of Intelligence and Computing, Tianjin University, China","Huawei Noah\u2019s Ark Lab, China"],"affiliations":[{"raw_affiliation_string":"College of Intelligence and Computing, Tianjin University, China","institution_ids":["https://openalex.org/I162868743"]},{"raw_affiliation_string":"Huawei Noah\u2019s Ark Lab, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035138959","display_name":"Zongzhang Zhang","orcid":"https://orcid.org/0000-0002-9238-4747"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zongzhang Zhang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China","School of Artificial Intelligence, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100639580","display_name":"Chao Qian","orcid":"https://orcid.org/0000-0002-3543-7507"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chao Qian","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, China","School of Artificial Intelligence, Nanjing University, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Artificial Intelligence, Nanjing University, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5100692130"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37384541,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8939","last_page":"8947"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.2703000009059906,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10551","display_name":"Scheduling and Optimization Algorithms","score":0.2703000009059906,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/regret","display_name":"Regret","score":0.6444000005722046},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6105999946594238},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4986000061035156},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.4129999876022339},{"id":"https://openalex.org/keywords/optimization-algorithm","display_name":"Optimization algorithm","score":0.39959999918937683},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.37630000710487366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7462000250816345},{"id":"https://openalex.org/C50817715","wikidata":"https://www.wikidata.org/wiki/Q79895177","display_name":"Regret","level":2,"score":0.6444000005722046},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6105999946594238},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5318999886512756},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4986000061035156},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4505000114440918},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4129999876022339},{"id":"https://openalex.org/C2987595161","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Optimization algorithm","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.3084000051021576},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.296099990606308},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2897000014781952},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28369998931884766},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2660999894142151}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/994","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/994","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Black-Box":[0],"Optimization":[1],"(BBO)":[2],"has":[3,16],"found":[4],"successful":[5],"applications":[6],"in":[7,21,76],"many":[8],"fields":[9],"of":[10,25,35,102,133,144,149,158],"science":[11],"and":[12,32,54,95,109,184],"engineering.":[13],"Recently,":[14],"there":[15],"been":[17],"a":[18,66,70],"growing":[19],"interest":[20],"meta-learning":[22],"particular":[23],"components":[24],"BBO":[26,71,180],"algorithms":[27,94],"to":[28,68,85,105,114,118,129,154,165],"speed":[29],"up":[30],"optimization":[31,88,121],"get":[33],"rid":[34],"tedious":[36],"hand-crafted":[37],"heuristics.":[38],"As":[39],"an":[40,77,134],"extension,":[41],"learning":[42,100],"the":[43,49,57,87,98,120,131,141,145,166],"entire":[44],"algorithm":[45,72,135],"from":[46,52,73],"data":[47,75],"requires":[48],"least":[50],"labor":[51],"experts":[53],"can":[55],"provide":[56],"most":[58],"flexibility.":[59],"In":[60],"this":[61],"paper,":[62],"we":[63],"propose":[64],"RIBBO,":[65],"method":[67,116],"reinforce-learn":[69],"offline":[74],"end-to-end":[78],"fashion.":[79],"RIBBO":[80,153],"employs":[81],"expressive":[82],"sequence":[83],"models":[84,104],"learn":[86],"histories":[89,122],"produced":[90],"by":[91,170],"multiple":[92],"behavior":[93],"tasks,":[96],"leveraging":[97],"in-context":[99],"ability":[101],"large":[103],"extract":[106],"task":[107],"information":[108],"make":[110],"decisions":[111],"accordingly.":[112],"Central":[113],"our":[115],"is":[117],"augment":[119],"with":[123],"regret-to-go":[124,150],"tokens,":[125],"which":[126],"are":[127,162],"designed":[128],"represent":[130],"performance":[132,175],"based":[136],"on":[137,176],"cumulative":[138],"regret":[139],"over":[140],"future":[142],"part":[143],"histories.":[146],"The":[147],"integration":[148],"tokens":[151],"enables":[152],"automatically":[155],"generate":[156],"sequences":[157],"query":[159],"points":[160],"that":[161],"positively":[163],"correlated":[164],"user-desired":[167],"regret,":[168],"verified":[169],"its":[171],"universally":[172],"good":[173],"empirical":[174],"diverse":[177],"problems,":[178],"including":[179],"benchmark,":[181],"hyper-parameter":[182],"optimization,":[183],"robot":[185],"control":[186],"problems.":[187]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}
