{"id":"https://openalex.org/W7163575895","doi":"https://doi.org/10.48550/arxiv.2606.04661","title":"CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts","display_name":"CRAFT: Cost-aware Refinement And Front-aware Tuning of Prompts","publication_year":2026,"publication_date":"2026-06-03","ids":{"openalex":"https://openalex.org/W7163575895","doi":"https://doi.org/10.48550/arxiv.2606.04661"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.04661","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04661","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":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.04661","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5137875067","display_name":"Shanu Kumar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kumar, Shanu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137860644","display_name":"Shubhanshu Khandelwal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Khandelwal, Shubhanshu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114620124","display_name":"Akhila Yesantarao Venkata","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Venkata, Akhila Yesantarao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137910936","display_name":"Parag Agrawal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Agrawal, Parag","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137873811","display_name":"Yova Kementchedjhieva","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kementchedjhieva, Yova","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5137904274","display_name":"Manish Gupta","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gupta, Manish","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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.19359999895095825,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.19359999895095825,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.1378999948501587,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.07190000265836716,"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/task","display_name":"Task (project management)","score":0.6865000128746033},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.4885999858379364},{"id":"https://openalex.org/keywords/pareto-principle","display_name":"Pareto principle","score":0.40119999647140503},{"id":"https://openalex.org/keywords/raising","display_name":"Raising (metalworking)","score":0.3652999997138977},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.3458000123500824},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.3456999957561493},{"id":"https://openalex.org/keywords/pareto-optimal","display_name":"Pareto optimal","score":0.3253999948501587}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6865000128746033},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.680400013923645},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4885999858379364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4154999852180481},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40950000286102295},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.40119999647140503},{"id":"https://openalex.org/C2780589192","wikidata":"https://www.wikidata.org/wiki/Q7285140","display_name":"Raising (metalworking)","level":2,"score":0.3652999997138977},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.359499990940094},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3458000123500824},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.3456999957561493},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3260999917984009},{"id":"https://openalex.org/C2986314615","wikidata":"https://www.wikidata.org/wiki/Q36829","display_name":"Pareto optimal","level":3,"score":0.3253999948501587},{"id":"https://openalex.org/C68781425","wikidata":"https://www.wikidata.org/wiki/Q2052203","display_name":"Multi-objective optimization","level":2,"score":0.29980000853538513},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2759999930858612},{"id":"https://openalex.org/C2777551076","wikidata":"https://www.wikidata.org/wiki/Q842332","display_name":"Front (military)","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.26570001244544983},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C80478641","wikidata":"https://www.wikidata.org/wiki/Q195771","display_name":"Sequential analysis","level":2,"score":0.2624000012874603},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.26109999418258667}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.04661","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04661","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":"doi:10.48550/arxiv.2606.04661","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.04661","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":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Prompts":[0],"tuned":[1],"for":[2,42],"accuracy":[3,36],"often":[4,62],"grow":[5],"long,":[6],"raising":[7],"inference":[8],"cost":[9,39],"on":[10,19],"every":[11],"model":[12],"call.":[13],"The":[14,45,157],"best":[15],"accuracy-cost":[16,158],"trade-off":[17,57,159],"depends":[18],"the":[20,23,32,49,56,69,95,104,120],"task":[21],"and":[22,37,61,98,112,124,134,143,149],"budget,":[24,123],"so":[25],"prompt":[26,87],"optimization":[27],"is":[28],"a":[29,52,65,71,85,128,161,165],"search":[30,60],"over":[31],"Pareto":[33],"front":[34],"of":[35,68],"prompt-token":[38],"rather":[40],"than":[41],"one":[43],"prompt.":[44],"usual":[46],"shortcut,":[47],"collapsing":[48],"objectives":[50],"into":[51],"weighted":[53],"sum,":[54],"fixes":[55],"weight":[58],"before":[59],"recovers":[63],"only":[64],"narrow":[66],"region":[67],"front,":[70],"failure":[72],"we":[73],"call":[74],"scalarization":[75],"collapse.":[76],"We":[77],"present":[78],"CRAFT":[79],"(Cost-aware":[80],"Refinement":[81],"And":[82],"Front-aware":[83],"Tuning),":[84],"Pareto-front":[86],"optimizer":[88],"that":[89],"treats":[90],"target-LLM":[91],"validation":[92,122],"calls":[93],"as":[94],"scarce":[96],"resource":[97],"allocates":[99],"them":[100],"to":[101],"candidates":[102],"near":[103],"optimistic":[105],"candidate":[106],"front.":[107],"Each":[108],"round,":[109],"complementary":[110],"accuracy-oriented":[111],"cost-oriented":[113],"generators":[114],"propose":[115],"edits,":[116],"Pareto-gap":[117],"acquisition":[118],"spends":[119],"per-round":[121],"NSGA-II":[125],"retention":[126],"keeps":[127],"spread-out":[129],"population.":[130],"Across":[131],"six":[132],"classification":[133],"reasoning":[135],"benchmarks,":[136],"CRAFT's":[137],"retained":[138],"fronts":[139],"reach":[140],"both":[141],"high-accuracy":[142],"low-cost":[144],"regions,":[145],"while":[146],"accuracy-only,":[147],"cost-only,":[148],"weighted-sum":[150],"baselines":[151],"each":[152],"concentrate":[153],"in":[154],"narrower":[155],"regions.":[156],"becomes":[160],"post-search":[162],"choice,":[163],"not":[164],"pre-search":[166],"weight.":[167]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-05T00:00:00"}