{"id":"https://openalex.org/W7213675688","doi":"https://doi.org/10.18653/2026.findings-emnlp.2131","title":"AutoData: Agentic Search for Pre-training Data Selection","display_name":"AutoData: Agentic Search for Pre-training Data Selection","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7213675688","doi":"https://doi.org/10.18653/2026.findings-emnlp.2131"},"language":"en","primary_location":{"id":"doi:10.18653/2026.findings-emnlp.2131","doi":"https://doi.org/10.18653/2026.findings-emnlp.2131","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.2131","pdf_url":"https://aclanthology.org/2026.findings-emnlp.2131.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://aclanthology.org/2026.findings-emnlp.2131.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5152236387","display_name":"Yan Meng","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yan Meng","raw_affiliation_strings":["University of Amsterdam , Amsterdam , The Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Amsterdam , Amsterdam , The Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136668553","display_name":"Dhruv Srikanth","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dhruv Srikanth","raw_affiliation_strings":["Weco AI , London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weco AI , London , UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5152204333","display_name":"Bingchen Zhao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bingchen Zhao","raw_affiliation_strings":["Weco AI , London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weco AI , London , UK","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109476084","display_name":"Zheng\u2010Yao Jiang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhengyao Jiang","raw_affiliation_strings":["Weco AI , London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weco AI , London , UK","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5011141204","display_name":"Yuxiang Wu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yuxiang Wu","raw_affiliation_strings":["Weco AI , London , UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Weco AI , London , UK","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.75736257,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"45474","last_page":"45491"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.7333999872207642,"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":0.7333999872207642,"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":0.09229999780654907,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.05979999899864197,"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/llm-based-agents","display_name":"LLM agents","score":0.8209999799728394},{"id":"https://openalex.org/keywords/agentic-search","display_name":"agentic search","score":0.7519999742507935},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.6980000138282776},{"id":"https://openalex.org/keywords/proxy-models","display_name":"proxy models","score":0.4009999930858612},{"id":"https://openalex.org/keywords/perplexity","display_name":"perplexity","score":0.6290000081062317},{"id":"https://openalex.org/keywords/lexical-statistics","display_name":"lexical statistics","score":0.6589999794960022},{"id":"https://openalex.org/keywords/stratification","display_name":"stratification","score":0.6119999885559082},{"id":"https://openalex.org/keywords/stochastic-selection","display_name":"stochastic selection","score":0.5320000052452087}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7627000212669373},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6628999710083008},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.636900007724762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5825999975204468},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.5717999935150146},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5328999757766724},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C5274069","wikidata":"https://www.wikidata.org/wiki/Q2285707","display_name":"Categorical variable","level":2,"score":0.4700999855995178},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.45730000734329224},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.4050999879837036},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3982999920845032},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.39010000228881836},{"id":"https://openalex.org/C126042441","wikidata":"https://www.wikidata.org/wiki/Q1324888","display_name":"Frame (networking)","level":2,"score":0.3765999972820282},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.36970001459121704},{"id":"https://openalex.org/C207850805","wikidata":"https://www.wikidata.org/wiki/Q269608","display_name":"Reverse engineering","level":2,"score":0.3517000079154968},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3513999879360199},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.3334999978542328},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.3305000066757202},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.3221000134944916},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.3147999942302704},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2824000120162964},{"id":"https://openalex.org/C2780148112","wikidata":"https://www.wikidata.org/wiki/Q1432581","display_name":"Proxy (statistics)","level":2,"score":0.27559998631477356},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2745000123977661},{"id":"https://openalex.org/C2780440489","wikidata":"https://www.wikidata.org/wiki/Q5227278","display_name":"Data-driven","level":2,"score":0.25859999656677246},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.2581999897956848}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.18653/2026.findings-emnlp.2131","doi":"https://doi.org/10.18653/2026.findings-emnlp.2131","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.2131","pdf_url":"https://aclanthology.org/2026.findings-emnlp.2131.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2609.19754","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.19754","pdf_url":"https://arxiv.org/pdf/2609.19754","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,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.18653/2026.findings-emnlp.2131","doi":"https://doi.org/10.18653/2026.findings-emnlp.2131","is_oa":true,"landing_page_url":"https://doi.org/10.18653/2026.findings-emnlp.2131","pdf_url":"https://aclanthology.org/2026.findings-emnlp.2131.pdf","source":{"id":"https://openalex.org/S7407096085","display_name":"Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/P4310320244","host_organization_name":"Association for Computational Linguistics","host_organization_lineage":["https://openalex.org/P4310320244"],"host_organization_lineage_names":["Association for Computational Linguistics"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Findings of the Association for Computational Linguistics: EMNLP 2026","raw_type":"proceedings-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7213675688.pdf","grobid_xml":"https://content.openalex.org/works/W7213675688.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7160932421","https://openalex.org/W7221778828","https://openalex.org/W4416157255","https://openalex.org/W7215031493","https://openalex.org/W7163066505","https://openalex.org/W7202307896","https://openalex.org/W7222429822","https://openalex.org/W4414981092","https://openalex.org/W4414819232","https://openalex.org/W7130729681"],"abstract_inverted_index":{"LLM":[0],"agents":[1],"have":[2],"recently":[3],"shown":[4],"promise":[5],"in":[6],"automating":[7],"machine":[8,142],"learning":[9,143],"engineering":[10,34,135],"by":[11,86],"editing":[12],"model":[13,149],"and":[14,43,78,125,150],"training":[15],"code":[16],"under":[17],"execution":[18],"feedback.Data,":[19],"however,":[20],"remains":[21],"largely":[22],"outside":[23],"this":[24,115],"agentic":[25,141],"optimisation":[26],"loop.We":[27],"frame":[28],"pre-training":[29],"data":[30,57,134],"selection":[31,54,80,103],"as":[32,139],"heuristic":[33],"over":[35,52,63],"per-document":[36],"features,":[37],"i.e.,":[38],"lexical":[39],"statistics,":[40],"categorical":[41],"labels,":[42],"perplexity.We":[44],"introduce":[45],"AutoData,":[46],"an":[47,97,140],"agent":[48],"that":[49,60,105,133],"searches":[50,70],"directly":[51],"executable":[53],"algorithms.Unlike":[55],"prior":[56],"mixture":[58],"methods":[59],"optimise":[61],"weights":[62],"a":[64,71,94,102],"fixed":[65],"set":[66],"of":[67,75],"domains,":[68],"AutoData":[69,100],"richer":[72],"program":[73],"space":[74],"scoring,":[76],"stratification,":[77],"stochastic":[79],"rules,":[81],"discovering":[82],"feature":[83],"interactions":[84],"automatically":[85],"iteratively":[87],"refining":[88],"algorithms":[89],"with":[90],"validation":[91],"feedback":[92],"from":[93,148],"proxy":[95],"model.Within":[96],"overnight":[98],"search,":[99],"discovers":[101],"algorithm":[104],"outperforms":[106],"existing":[107],"human-designed":[108],"curation":[109],"pipelines.Despite":[110],"being":[111],"searched":[112],"only":[113],"on":[114],"small":[116],"proxy,":[117],"the":[118,127,154],"discovered":[119],"recipe":[120],"transfers":[121],"to":[122,153],"larger":[123],"scales":[124],"improves":[126],"downstream":[128],"metric":[129],"CORE.These":[130],"results":[131],"suggest":[132],"can":[136],"be":[137],"treated":[138],"problem,":[144],"extending":[145],"autonomous":[146],"research":[147],"training-code":[151],"optimization":[152],"data.":[155]},"counts_by_year":[],"updated_date":"2026-11-02T09:45:03.842371","created_date":"2026-09-20T00:00:00"}