{"id":"https://openalex.org/W7214749019","doi":"https://doi.org/10.48550/arxiv.2609.34829","title":"From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction","display_name":"From Weak Task Specifications to Scientific Extraction Agents: Optimizing Task Construction","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214749019","doi":"https://doi.org/10.48550/arxiv.2609.34829"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34829","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34829","pdf_url":"https://arxiv.org/pdf/2609.34829","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"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2609.34829","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5153531547","display_name":"Zixiao Dong","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dong, Zixiao","raw_affiliation_strings":["School of Computer Science and Technology , University of Science and Technology of China","State Key Laboratory of Cognitive Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153537663","display_name":"Wei Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang, Wei","raw_affiliation_strings":["State Key Laboratory of Cognitive Intelligence","University of Science and Technology of China ,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence","institution_ids":[]},{"raw_affiliation_string":"University of Science and Technology of China ,","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153537525","display_name":"Zihao Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Zihao","raw_affiliation_strings":["School of Computer Science and Technology , University of Science and Technology of China","State Key Laboratory of Cognitive Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153533898","display_name":"Chenshu Li","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li, Chenshu","raw_affiliation_strings":["School of Computer Science and Technology , University of Science and Technology of China","State Key Laboratory of Cognitive Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153533812","display_name":"Longzhang Liu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liu, Longzhang","raw_affiliation_strings":["School of Computer Science and Technology , University of Science and Technology of China","State Key Laboratory of Cognitive Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153432673","display_name":"Tao Tan","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210103140","display_name":"CCCC Highway Consultants (China)","ror":"https://ror.org/01bs84e19","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103140"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tan, Tao","raw_affiliation_strings":["CCCC Second Highway Consultants Co. , Ltd"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CCCC Second Highway Consultants Co. , Ltd","institution_ids":["https://openalex.org/I4210103140"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153489306","display_name":"Hong Xie","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xie, Hong","raw_affiliation_strings":["School of Computer Science and Technology , University of Science and Technology of China","State Key Laboratory of Cognitive Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science and Technology , University of Science and Technology of China","institution_ids":["https://openalex.org/I126520041"]},{"raw_affiliation_string":"State Key Laboratory of Cognitive Intelligence","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.7890999913215637,"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":0.7890999913215637,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.03370000049471855,"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/T13910","display_name":"Computational and Text Analysis Methods","score":0.029999999329447746,"subfield":{"id":"https://openalex.org/subfields/3300","display_name":"General Social Sciences"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/schema-construction","display_name":"schema construction","score":0.5879999995231628},{"id":"https://openalex.org/keywords/evaluation-criteria","display_name":"evaluation criteria","score":0.5910000205039978}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897999882698059},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.6869999766349792},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6805999875068665},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.6736999750137329},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5831000208854675},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4101000130176544},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.37929999828338623},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36070001125335693},{"id":"https://openalex.org/C2777466982","wikidata":"https://www.wikidata.org/wiki/Q5227287","display_name":"Data extraction","level":3,"score":0.34310001134872437},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.33239999413490295},{"id":"https://openalex.org/C195807954","wikidata":"https://www.wikidata.org/wiki/Q1662562","display_name":"Information extraction","level":2,"score":0.3190999925136566},{"id":"https://openalex.org/C88482812","wikidata":"https://www.wikidata.org/wiki/Q6453666","display_name":"Modular programming","level":2,"score":0.31839999556541443},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.29840001463890076},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.2865000069141388},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.2849000096321106},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2768999934196472},{"id":"https://openalex.org/C55439883","wikidata":"https://www.wikidata.org/wiki/Q360812","display_name":"Correctness","level":2,"score":0.2761000096797943}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34829","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34829","pdf_url":"https://arxiv.org/pdf/2609.34829","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"},{"id":"doi:10.48550/arxiv.2609.34829","doi":"https://doi.org/10.48550/arxiv.2609.34829","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34829","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,"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2609.34829","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34829","pdf_url":"https://arxiv.org/pdf/2609.34829","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"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6036844487","display_name":null,"funder_award_id":"XDA0490000","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214749019.pdf","grobid_xml":"https://content.openalex.org/works/W7214749019.grobid-xml"},"referenced_works_count":2,"referenced_works":["https://openalex.org/W7131248149","https://openalex.org/W7170175357"],"related_works":["https://openalex.org/W7196956905","https://openalex.org/W7204908307","https://openalex.org/W7211905994","https://openalex.org/W7214764339","https://openalex.org/W4415344867","https://openalex.org/W7164491461","https://openalex.org/W7203923425","https://openalex.org/W4416037168","https://openalex.org/W7169507081","https://openalex.org/W7213660427"],"abstract_inverted_index":{"Most":[0],"methods":[1],"that":[2,10],"optimize":[3],"LLM":[4],"prompts":[5],"and":[6,16,61,83,91,122,127,139],"agent":[7],"workflows":[8],"assume":[9],"task-specific":[11,50,79],"output":[12],"schemas,":[13],"extraction":[14,23,81,92,128],"instructions,":[15,82],"evaluation":[17,107,142],"criteria":[18,108],"are":[19],"predefined.":[20],"For":[21],"scientific":[22],"agents,":[24],"however,":[25],"a":[26,53,58,71,78,114],"short":[27,59],"task":[28],"goal":[29,60],"may":[30],"not":[31],"fully":[32],"determine":[33],"these":[34],"components,":[35],"while":[36,105],"specifying":[37],"them":[38],"manually":[39],"is":[40],"costly.":[41],"We":[42],"study":[43],"the":[44,49,144],"upstream":[45],"problem":[46],"of":[47],"constructing":[48],"configuration":[51],"from":[52],"weak":[54],"specification":[55],"containing":[56],"only":[57],"unannotated":[62],"reference":[63],"documents.":[64],"Rather":[65],"than":[66],"treating":[67],"automatic":[68,118],"construction":[69,90,119,126],"as":[70],"fixed":[72],"preprocessing":[73],"step,":[74],"our":[75],"framework":[76],"constructs":[77],"schema,":[80],"base":[84],"training":[85],"rubrics,":[86],"then":[87],"keeps":[88],"schema":[89,125],"instructions":[93,129],"editable":[94],"during":[95],"optimization.":[96],"Failure-focused":[97],"updates":[98],"concentrate":[99],"textual-gradient":[100],"feedback":[101],"on":[102],"lower-scoring":[103],"documents,":[104],"training-time":[106],"adapt":[109],"to":[110],"recurring":[111],"failures.":[112],"On":[113],"heterogeneous-catalysis":[115],"literature":[116],"corpus,":[117],"remains":[120],"improvable,":[121],"optimizing":[123],"both":[124],"performs":[130],"best":[131],"across":[132],"all":[133],"four":[134],"judge-rubric":[135],"settings,":[136],"with":[137],"ablations":[138],"blinded":[140],"human":[141],"supporting":[143],"proposed":[145],"formulation.":[146]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}