{"id":"https://openalex.org/W7164297222","doi":"https://doi.org/10.48550/arxiv.2606.11459","title":"APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection","display_name":"APEX: Automated Prompt Engineering eXpert with Dynamic Data Selection","publication_year":2026,"publication_date":"2026-06-09","ids":{"openalex":"https://openalex.org/W7164297222","doi":"https://doi.org/10.48550/arxiv.2606.11459"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.11459","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11459","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":null,"license_id":null,"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.2606.11459","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5138467966","display_name":"Fei Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Fei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138475993","display_name":"Si Si","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Si, Si","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138402250","display_name":"Cho-Jui Hsieh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hsieh, Cho-Jui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5063459703","display_name":"Inderjit S. Dhillon","orcid":"https://orcid.org/0000-0002-2759-1416"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhillon, Inderjit S.","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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.19920000433921814,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T10743","display_name":"Software Testing and Debugging Techniques","score":0.19920000433921814,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.15880000591278076,"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/T10848","display_name":"Advanced Multi-Objective Optimization Algorithms","score":0.08669999986886978,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/key","display_name":"Key (lock)","score":0.5049999952316284},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.45719999074935913},{"id":"https://openalex.org/keywords/apex","display_name":"Apex (geometry)","score":0.43560001254081726},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.29190000891685486},{"id":"https://openalex.org/keywords/dynamic-data","display_name":"Dynamic data","score":0.2768999934196472}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809000015258789},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5049999952316284},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48539999127388},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.47760000824928284},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46619999408721924},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.45719999074935913},{"id":"https://openalex.org/C67139541","wikidata":"https://www.wikidata.org/wiki/Q2858200","display_name":"Apex (geometry)","level":2,"score":0.43560001254081726},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.29190000891685486},{"id":"https://openalex.org/C197298091","wikidata":"https://www.wikidata.org/wiki/Q5318963","display_name":"Dynamic data","level":2,"score":0.2768999934196472},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.27489998936653137},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.2653000056743622}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.11459","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11459","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.11459","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.11459","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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4982048571109772,"id":"https://metadata.un.org/sdg/9"}],"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],"are":[3],"highly":[4],"sensitive":[5],"to":[6,13,147,178],"prompt":[7,11,72,155,182],"formulation,":[8],"necessitating":[9],"automatic":[10],"optimization":[12,88],"unlock":[14],"their":[15],"full":[16],"potential.":[17],"While":[18],"evolutionary":[19],"algorithms":[20],"have":[21],"emerged":[22],"as":[23,41],"the":[24,38,67,71,77,87,92,97,100,110,118,153],"dominant":[25],"paradigm,":[26],"they":[27],"suffer":[28],"from":[29],"a":[30,42,62,139,173],"critical":[31],"bottleneck:":[32],"data":[33,68,98,149],"efficiency.":[34],"Current":[35],"methods":[36],"treat":[37],"development":[39],"dataset":[40,78],"static":[43],"benchmark,":[44],"wasting":[45],"significant":[46],"compute":[47],"budget":[48,141],"on":[49,86,161,167],"uninformative":[50],"data.":[51],"In":[52],"this":[53],"work,":[54],"we":[55,105],"introduce":[56],"APEX":[57,74,127,151],"(Automatic":[58],"Prompt":[59],"Engineering":[60],"eXpert),":[61],"novel":[63],"framework":[64],"that":[65,172],"optimizes":[66],"usage":[69],"alongside":[70],"search.":[73],"dynamically":[75],"stratifies":[76],"into":[79],"Easy,":[80],"Hard,":[81],"and":[82,117,135,165,180],"Mixed":[83,93],"tiers":[84],"based":[85],"lineage.":[89],"By":[90],"prioritizing":[91],"tier,":[94],"which":[95],"identifies":[96],"where":[99],"LLM":[101],"has":[102],"mixed":[103],"performance,":[104],"identify":[106],"two":[107],"high-leverage":[108],"subsets:":[109],"addressable":[111],"frontier":[112,120],"for":[113,121],"generating":[114],"informative":[115],"mutations":[116],"rank-sensitive":[119],"distinguishing":[122],"candidate":[123],"quality.":[124],"We":[125],"evaluate":[126],"across":[128],"three":[129],"diverse":[130],"benchmarks:":[131],"IFBench,":[132],"SimpleQA":[133],"Verified,":[134],"FACTS":[136],"Grounding.":[137],"Under":[138],"fixed":[140],"of":[142,159],"5,000":[143],"evaluation":[144],"calls,":[145],"due":[146],"its":[148],"efficiency,":[150],"outperforms":[152],"initial":[154],"by":[156],"an":[157],"average":[158],"11.2%":[160],"Gemini":[162],"2.5":[163],"Flash":[164],"6.8%":[166],"Gemma":[168],"3":[169],"27B,":[170],"demonstrating":[171],"data-centric":[174],"approach":[175],"is":[176],"key":[177],"efficient":[179],"effective":[181],"optimization.":[183]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-06-12T00:00:00"}