{"id":"https://openalex.org/W7161763877","doi":"https://doi.org/10.48550/arxiv.2605.18869","title":"MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization","display_name":"MO-CAPO: Multi-Objective Cost-Aware Prompt Optimization","publication_year":2026,"publication_date":"2026-05-15","ids":{"openalex":"https://openalex.org/W7161763877","doi":"https://doi.org/10.48550/arxiv.2605.18869"},"language":null,"primary_location":{"id":"pmh:oai:zenodo.org:21509145","is_oa":true,"landing_page_url":"https://arxiv.org/abs/arXiv:2605.18869","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/abs/arXiv:2605.18869","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5106102155","display_name":"Jan B\u00fcssing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B\u00fcssing, Jan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119949049","display_name":"Moritz Schlager","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schlager, Moritz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136594073","display_name":"Timo Hei\u00df","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hei\u00df, Timo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119949048","display_name":"Tom Zehle","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zehle, Tom","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5054262288","display_name":"Matthias Feurer","orcid":"https://orcid.org/0000-0001-9611-8588"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feurer, Matthias","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":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.13689999282360077,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.13689999282360077,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.125,"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/T10028","display_name":"Topic Modeling","score":0.08789999783039093,"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/inference","display_name":"Inference","score":0.6729000210762024},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5824999809265137},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.5594000220298767},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5026999711990356},{"id":"https://openalex.org/keywords/multi-objective-optimization","display_name":"Multi-objective optimization","score":0.5008999705314636},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.49540001153945923},{"id":"https://openalex.org/keywords/performance-metric","display_name":"Performance metric","score":0.48249998688697815},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.4584999978542328}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.739300012588501},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6729000210762024},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5824999809265137},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5680999755859375},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5594000220298767},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5026999711990356},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.5008999705314636},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.49540001153945923},{"id":"https://openalex.org/C2780898871","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Performance metric","level":2,"score":0.48249998688697815},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4584999978542328},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.4526999890804291},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4514999985694885},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.4058000147342682},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3939000070095062},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.384799987077713},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.319599986076355},{"id":"https://openalex.org/C193254401","wikidata":"https://www.wikidata.org/wiki/Q2160088","display_name":"Robust optimization","level":2,"score":0.3183000087738037},{"id":"https://openalex.org/C148764684","wikidata":"https://www.wikidata.org/wiki/Q621751","display_name":"Approximation algorithm","level":2,"score":0.2903999984264374},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26350000500679016},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.25369998812675476},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.25189998745918274}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:zenodo.org:21509145","is_oa":true,"landing_page_url":"https://arxiv.org/abs/arXiv:2605.18869","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/preprint"},{"id":"doi:10.48550/arxiv.2605.18869","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.18869","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:21509145","is_oa":true,"landing_page_url":"https://arxiv.org/abs/arXiv:2605.18869","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/preprint"},"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":{"Large":[0],"language":[1],"models":[2],"(LLMs)":[3],"achieve":[4],"strong":[5],"performance":[6,32,75,240],"across":[7,106],"a":[8,61,66,89,166,216],"wide":[9],"range":[10],"of":[11,99,149,154,199,220,233],"tasks":[12,108],"but":[13],"are":[14,179],"highly":[15],"sensitive":[16],"to":[17,115,226],"prompt":[18,25,51,69,123],"design,":[19],"motivating":[20],"the":[21,44,95,143,155,185,196],"need":[22],"for":[23,83],"automatic":[24],"optimization.":[26,85],"Existing":[27],"methods":[28],"predominantly":[29],"focus":[30],"on":[31,49,54,146],"alone,":[33],"ignoring":[34,57],"competing":[35],"objectives":[36],"such":[37],"as":[38],"inference":[39,77],"cost":[40,78,91],"or":[41],"latency.":[42],"At":[43],"same":[45],"time,":[46],"existing":[47],"work":[48],"multi-objective":[50,68,118,200],"optimization":[52,58,70],"relies":[53],"off-the-shelf":[55],"NSGA-II,":[56],"efficiency.":[59],"As":[60],"remedy,":[62],"we":[63,194],"introduce":[64],"MO-CAPO,":[65],"novel":[67],"algorithm":[71],"that":[72,93,127,178,204],"jointly":[73],"optimizes":[74],"and":[76,109,112,120,133,159,207,212,241],"while":[79,138],"leveraging":[80],"budget":[81],"allocation":[82],"cost-efficient":[84],"We":[86,102],"further":[87],"propose":[88],"deployment-oriented":[90],"objective":[92],"captures":[94],"full":[96],"computational":[97],"profile":[98],"LLM":[100],"inference.":[101],"evaluate":[103],"our":[104],"approach":[105],"four":[107],"three":[110],"LLMs":[111],"compare":[113],"it":[114],"an":[116,229],"NSGA-II-based":[117],"method":[119],"state-of-the-art":[121],"single-objective":[122,182,191],"optimizers.":[124],"Results":[125],"show":[126],"MO-CAPO":[128,223],"consistently":[129],"identifies":[130],"strong,":[131],"robust,":[132],"diverse":[134,175],"Pareto":[135],"front":[136],"approximations":[137],"maintaining":[139],"cost-efficiency.":[140],"It":[141],"outperforms":[142],"NSGA-II":[144],"baseline":[145],"8":[147],"out":[148],"12":[150],"cases":[151],"in":[152],"terms":[153],"noisy":[156,210],"R2":[157,211],"metric":[158],"achieves":[160],"competitive":[161,189],"performances":[162],"often":[163],"already":[164],"at":[165],"considerably":[167],"lower":[168],"budget.":[169],"The":[170],"discovered":[171,231],"solution":[172,221],"sets":[173],"span":[174],"performance-cost":[176],"trade-offs":[177,238],"omitted":[180],"by":[181],"optimizers,":[183],"yet":[184],"top-performance":[186],"candidates":[187],"remain":[188],"with":[190],"solutions.":[192],"Additionally,":[193],"conduct":[195],"first":[197],"evaluation":[198],"machine":[201],"learning":[202],"experiments":[203],"considers":[205],"generalization":[206],"robustness":[208],"through":[209],"approximation":[213],"gap,":[214],"enabling":[215],"more":[217],"realistic":[218],"assessment":[219],"quality.":[222],"enables":[224],"practitioners":[225],"select":[227],"from":[228],"efficiently":[230],"set":[232],"multiple":[234],"prompts":[235],"offering":[236],"different":[237],"between":[239],"cost.":[242]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-05-21T00:00:00"}