{"id":"https://openalex.org/W4412673520","doi":"https://doi.org/10.1145/3731120.3744584","title":"Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization","display_name":"Learning to Rank for Multiple Retrieval-Augmented Models through Iterative Utility Maximization","publication_year":2025,"publication_date":"2025-07-18","ids":{"openalex":"https://openalex.org/W4412673520","doi":"https://doi.org/10.1145/3731120.3744584"},"language":"en","primary_location":{"id":"doi:10.1145/3731120.3744584","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731120.3744584","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744584?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744584?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082594835","display_name":"Alireza Salemi","orcid":"https://orcid.org/0009-0006-1937-2615"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Alireza Salemi","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101457713","display_name":"Hamed Zamani","orcid":"https://orcid.org/0000-0002-0800-3340"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hamed Zamani","raw_affiliation_strings":["University of Massachusetts Amherst, Amherst, MA, USA"],"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst, Amherst, MA, USA","institution_ids":["https://openalex.org/I24603500"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082594835"],"corresponding_institution_ids":["https://openalex.org/I24603500"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08851348,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"183","last_page":"193"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T10028","display_name":"Topic Modeling","score":0.9998000264167786,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980000257492065,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9976000189781189,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7554306983947754},{"id":"https://openalex.org/keywords/maximization","display_name":"Maximization","score":0.6275970935821533},{"id":"https://openalex.org/keywords/rank","display_name":"Rank (graph theory)","score":0.6075688004493713},{"id":"https://openalex.org/keywords/learning-to-rank","display_name":"Learning to rank","score":0.5303714275360107},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4542449712753296},{"id":"https://openalex.org/keywords/iterative-method","display_name":"Iterative method","score":0.4476097822189331},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3552172780036926},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.34521543979644775},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2224428951740265},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17806866765022278},{"id":"https://openalex.org/keywords/ranking","display_name":"Ranking (information retrieval)","score":0.13722819089889526}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7554306983947754},{"id":"https://openalex.org/C2776330181","wikidata":"https://www.wikidata.org/wiki/Q18358244","display_name":"Maximization","level":2,"score":0.6275970935821533},{"id":"https://openalex.org/C164226766","wikidata":"https://www.wikidata.org/wiki/Q7293202","display_name":"Rank (graph theory)","level":2,"score":0.6075688004493713},{"id":"https://openalex.org/C86037889","wikidata":"https://www.wikidata.org/wiki/Q4330127","display_name":"Learning to rank","level":3,"score":0.5303714275360107},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4542449712753296},{"id":"https://openalex.org/C159694833","wikidata":"https://www.wikidata.org/wiki/Q2321565","display_name":"Iterative method","level":2,"score":0.4476097822189331},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3552172780036926},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.34521543979644775},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2224428951740265},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17806866765022278},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.13722819089889526},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3731120.3744584","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731120.3744584","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744584?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3731120.3744584","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3731120.3744584","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3731120.3744584?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International ACM SIGIR Conference on Innovative Concepts and Theories in Information Retrieval (ICTIR)","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2455356981","display_name":"Bayesian Model Averaging for Nuclear Effective Field Teories","funder_award_id":"2412612","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3761471208","display_name":"Collaborative Research:  Biomass Burning Emissions Over Southern Africa","funder_award_id":"0001424","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6256039072","display_name":"Collaborative Research: III: Medium: Retrieval-Enhanced Machine Learning Through an Information Retrieval Lens","funder_award_id":"2402873","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8876996369","display_name":null,"funder_award_id":"N00014","funder_id":"https://openalex.org/F4320337345","funder_display_name":"Office of Naval Research"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320337345","display_name":"Office of Naval Research","ror":"https://ror.org/00rk2pe57"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4412673520.pdf","grobid_xml":"https://content.openalex.org/works/W4412673520.grobid-xml"},"referenced_works_count":43,"referenced_works":["https://openalex.org/W1979964376","https://openalex.org/W1996924157","https://openalex.org/W2084413241","https://openalex.org/W2122946987","https://openalex.org/W2125771191","https://openalex.org/W2130062883","https://openalex.org/W2145413874","https://openalex.org/W2149427297","https://openalex.org/W2492794003","https://openalex.org/W2507134384","https://openalex.org/W2889787757","https://openalex.org/W2912924812","https://openalex.org/W2914304175","https://openalex.org/W2923014074","https://openalex.org/W2962881743","https://openalex.org/W2963339397","https://openalex.org/W2963341956","https://openalex.org/W2963748441","https://openalex.org/W2963961878","https://openalex.org/W2981852735","https://openalex.org/W2990138404","https://openalex.org/W3034999214","https://openalex.org/W3099700870","https://openalex.org/W3155807546","https://openalex.org/W3156789018","https://openalex.org/W3169283738","https://openalex.org/W3174821868","https://openalex.org/W3217305727","https://openalex.org/W4226321975","https://openalex.org/W4229065825","https://openalex.org/W4288089799","https://openalex.org/W4301243929","https://openalex.org/W4317898419","https://openalex.org/W4384774018","https://openalex.org/W4385573236","https://openalex.org/W4385688545","https://openalex.org/W4391156274","https://openalex.org/W4394773691","https://openalex.org/W4400525546","https://openalex.org/W4400526126","https://openalex.org/W4400528650","https://openalex.org/W4400529966","https://openalex.org/W4402671806"],"related_works":["https://openalex.org/W2112835755","https://openalex.org/W4291951920","https://openalex.org/W2349674371","https://openalex.org/W2097495471","https://openalex.org/W1696545756","https://openalex.org/W2772359885","https://openalex.org/W2899331914","https://openalex.org/W3011471740","https://openalex.org/W2954428433","https://openalex.org/W2572315477"],"abstract_inverted_index":{"This":[0,60],"paper":[1],"investigates":[2],"the":[3,36,43,50,53,68,76,93,109,119,145,153],"design":[4],"of":[5,52,78,113,167],"a":[6,19,159],"unified":[7],"search":[8,37,69,94],"engine":[9,38,70,95],"to":[10,65,88,96,106,163],"serve":[11,108],"multiple":[12],"retrieval-augmented":[13],"generation":[14],"(RAG)":[15],"agents,":[16],"each":[17,80,112,148],"with":[18,75],"distinct":[20],"task,":[21],"backbone":[22],"large":[23],"language":[24],"model":[25],"(LLM),":[26],"and":[27,46],"RAG":[28,44,136,149],"strategy.":[29],"We":[30,138],"introduce":[31],"an":[32,57,72,89],"iterative":[33],"approach":[34,128],"where":[35],"generates":[39],"retrieval":[40,146],"results":[41,110],"for":[42,111,147],"agents":[45,104],"gathers":[47],"feedback":[48,61,105],"on":[49,101,116,130,152],"quality":[51],"retrieved":[54],"documents":[55],"during":[56],"offline":[58],"phase.":[59],"is":[62],"then":[63],"used":[64],"iteratively":[66],"optimize":[67],"using":[71],"expectation-maximization":[73],"algorithm,":[74],"goal":[77],"maximizing":[79],"agent's":[81],"utility":[82],"function.":[83],"Additionally,":[84],"we":[85,157],"adapt":[86],"this":[87],"online":[90],"setting,":[91],"allowing":[92],"refine":[97],"its":[98],"behavior":[99],"based":[100,151],"real-time":[102],"individual":[103],"better":[107],"them.":[114],"Experiments":[115],"datasets":[117],"from":[118],"Knowledge-Intensive":[120],"Language":[121],"Tasks":[122],"(KILT)":[123],"benchmark":[124],"demonstrates":[125],"that":[126,140],"our":[127,141,168],"significantly":[129],"average":[131],"outperforms":[132],"baselines":[133],"across":[134],"18":[135],"models.":[137],"demonstrate":[139],"method":[142],"effectively":[143],"''personalizes''":[144],"agent":[150],"collected":[154],"feedback.":[155],"Finally,":[156],"provide":[158],"comprehensive":[160],"ablation":[161],"study":[162],"explore":[164],"various":[165],"aspects":[166],"method.":[169]},"counts_by_year":[],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}