{"id":"https://openalex.org/W7170433916","doi":"https://doi.org/10.48550/arxiv.2607.20528","title":"PromptPack: Scaling LLM Annotation Agents for Online Recommendation","display_name":"PromptPack: Scaling LLM Annotation Agents for Online Recommendation","publication_year":2026,"publication_date":"2026-07-10","ids":{"openalex":"https://openalex.org/W7170433916","doi":"https://doi.org/10.48550/arxiv.2607.20528"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.20528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20528","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.2607.20528","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5028830288","display_name":"Sebastian Koralewski","orcid":"https://orcid.org/0000-0002-3213-5562"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Koralewski, Sebastian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044958229","display_name":"Merwan Barlier","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Barlier, Merwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119556740","display_name":"Yulia Stolin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stolin, Yulia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5007096285","display_name":"Bla\u017e \u0160krlj","orcid":"https://orcid.org/0000-0002-9916-8756"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"\u0160krlj, Bla\u017e","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/T10028","display_name":"Topic Modeling","score":0.14720000326633453,"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":0.14720000326633453,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.08739999681711197,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11948","display_name":"Machine Learning in Materials Science","score":0.07569999992847443,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.6460000276565552},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46160000562667847},{"id":"https://openalex.org/keywords/metric","display_name":"Metric (unit)","score":0.45730000734329224},{"id":"https://openalex.org/keywords/lift","display_name":"Lift (data mining)","score":0.44029998779296875},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.4327000081539154},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4198000133037567},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.4081999957561493},{"id":"https://openalex.org/keywords/image-retrieval","display_name":"Image retrieval","score":0.39160001277923584}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8389000296592712},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.6460000276565552},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46160000562667847},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C139002025","wikidata":"https://www.wikidata.org/wiki/Q3001212","display_name":"Lift (data mining)","level":2,"score":0.44029998779296875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.435699999332428},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.4327000081539154},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4198000133037567},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4081999957561493},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39899998903274536},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.39160001277923584},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.37880000472068787},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.3271999955177307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.325300008058548},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.2978000044822693},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C551230270","wikidata":"https://www.wikidata.org/wiki/Q4368942","display_name":"Data retrieval","level":2,"score":0.27149999141693115},{"id":"https://openalex.org/C2778348673","wikidata":"https://www.wikidata.org/wiki/Q739302","display_name":"Production (economics)","level":2,"score":0.2705000042915344},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.2702000141143799},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.2535000145435333},{"id":"https://openalex.org/C199579030","wikidata":"https://www.wikidata.org/wiki/Q2851778","display_name":"Automatic image annotation","level":4,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.20528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20528","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.2607.20528","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.20528","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":{"Online":[0],"recommendation":[1],"platforms":[2],"increasingly":[3],"use":[4],"Large":[5],"Language":[6],"Models":[7],"(LLMs)":[8],"to":[9,39,92,142],"extract":[10],"structured":[11],"features":[12],"from":[13],"ad":[14],"creatives.":[15],"While":[16],"deploying":[17],"a":[18,64,78,82,111,130],"single-call":[19],"LLM":[20,67,155],"annotation":[21,68],"agent":[22],"yields":[23],"significant":[24],"Click-Through":[25],"Rate":[26],"(CTR)":[27],"improvements":[28],"in":[29,46],"our":[30,143,154],"live":[31],"production":[32,146],"environment,":[33],"per-creative":[34],"prompting":[35],"is":[36],"prohibitively":[37],"expensive":[38],"scale.":[40],"The":[41],"redundant":[42],"system":[43,80],"instructions":[44],"sent":[45],"every":[47],"request":[48],"account":[49],"for":[50],"94%":[51],"of":[52,137],"billed":[53],"input":[54],"tokens.":[55],"To":[56,115],"break":[57],"this":[58,72],"cost":[59],"bottleneck,":[60],"we":[61,121],"introduce":[62,125],"PromptPack,":[63],"scalable,":[65],"high-throughput":[66],"agent.":[69],"PromptPack":[70,104,148],"achieves":[71],"scale":[73],"via":[74,105],"in-context":[75],"batching,":[76],"combining":[77],"shared":[79],"prompt,":[81],"strict":[83],"XML":[84],"structural":[85],"envelope,":[86],"and":[87,124,159],"an":[88,106],"output":[89],"correction":[90],"layer":[91],"ensure":[93],"deterministic,":[94],"pipeline-ready":[95],"feature":[96],"extraction":[97],"across":[98],"multiple":[99],"creatives":[100],"simultaneously.":[101],"We":[102],"evaluate":[103],"offline":[107],"retrieval":[108],"benchmark":[109],"using":[110],"downstream":[112],"logistic-regression":[113],"ranker.":[114],"deeply":[116],"profile":[117],"the":[118,134,138],"agent's":[119],"behavior,":[120],"measure":[122],"AUC":[123],"Volume-Weighted":[126],"Absolute":[127],"Lift":[128],"(VWAL),":[129],"novel":[131],"metric":[132],"capturing":[133],"signal":[135],"quality":[136],"generated":[139],"features.":[140],"Compared":[141],"live,":[144],"unbatched":[145],"baseline,":[147],"at":[149],"batch":[150],"size":[151],"20":[152],"cuts":[153],"costs":[156],"by":[157,162],"89%":[158],"accelerates":[160],"throughput":[161],"2.5x":[163],"while":[164],"fully":[165],"preserving":[166],"AUC.":[167]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-25T00:00:00"}