{"id":"https://openalex.org/W7225197771","doi":"https://doi.org/10.48550/arxiv.2611.03238","title":"ScienceCUA: Resource-to-Skill Construction and Execution-Guided Skill Evolution for Scientific Computer Use Agents","display_name":"ScienceCUA: Resource-to-Skill Construction and Execution-Guided Skill Evolution for Scientific Computer Use Agents","publication_year":2026,"publication_date":"2026-11-02","ids":{"openalex":"https://openalex.org/W7225197771","doi":"https://doi.org/10.48550/arxiv.2611.03238"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2611.03238","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03238","pdf_url":"https://arxiv.org/pdf/2611.03238","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/2611.03238","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160442481","display_name":"Daiqiang Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Daiqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136029511","display_name":"Jingyi Peng","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Peng, Jingyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083665930","display_name":"Rui Hua Hu","orcid":"https://orcid.org/0000-0001-7799-5198","observed_orcids":["https://orcid.org/0000-0001-7799-5198"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Rui","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160520606","display_name":"Jia Li","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Jia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160462557","display_name":"Xuyang Liu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xuyang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044179456","display_name":"Guanren Qiao","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qiao, Guanren","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018649889","display_name":"Yujia Xiang","orcid":"https://orcid.org/0000-0002-5070-6816","observed_orcids":["https://orcid.org/0000-0002-5070-6816"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiang, Yujia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5160443407","display_name":"Qiuzhuang Sun","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sun, Qiuzhuang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5149986451","display_name":"Zhiping Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Zhiping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5147715784","display_name":"Mingrui Luo","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Mingrui","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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3578999936580658,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.3578999936580658,"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/T10260","display_name":"Software Engineering Research","score":0.13779999315738678,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11986","display_name":"Scientific Computing and Data Management","score":0.12120000272989273,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/skill-evolution","display_name":"skill evolution","score":0.718999981880188},{"id":"https://openalex.org/keywords/software-documentation","display_name":"software documentation","score":0.5099999904632568},{"id":"https://openalex.org/keywords/benchmark-design","display_name":"benchmark design","score":0.42800000309944153},{"id":"https://openalex.org/keywords/llm-based-agents","display_name":"LLM agents","score":0.4690000116825104}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7318000197410583},{"id":"https://openalex.org/C56666940","wikidata":"https://www.wikidata.org/wiki/Q788790","display_name":"Documentation","level":2,"score":0.6546000242233276},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.6363999843597412},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6234999895095825},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.5995000004768372},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5496000051498413},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.48010000586509705},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4749999940395355},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3962000012397766},{"id":"https://openalex.org/C186846655","wikidata":"https://www.wikidata.org/wiki/Q3398377","display_name":"Software construction","level":4,"score":0.36250001192092896},{"id":"https://openalex.org/C149091818","wikidata":"https://www.wikidata.org/wiki/Q2429814","display_name":"Software system","level":3,"score":0.359499990940094},{"id":"https://openalex.org/C161821725","wikidata":"https://www.wikidata.org/wiki/Q917415","display_name":"Regression testing","level":5,"score":0.3587000072002411},{"id":"https://openalex.org/C202105479","wikidata":"https://www.wikidata.org/wiki/Q265013","display_name":"Software evolution","level":5,"score":0.3490999937057495},{"id":"https://openalex.org/C529173508","wikidata":"https://www.wikidata.org/wiki/Q638608","display_name":"Software development","level":3,"score":0.34610000252723694},{"id":"https://openalex.org/C117447612","wikidata":"https://www.wikidata.org/wiki/Q1412670","display_name":"Software quality","level":4,"score":0.3296000063419342},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.3248000144958496},{"id":"https://openalex.org/C101317890","wikidata":"https://www.wikidata.org/wiki/Q940053","display_name":"Software maintenance","level":4,"score":0.32269999384880066},{"id":"https://openalex.org/C82214349","wikidata":"https://www.wikidata.org/wiki/Q657339","display_name":"Software metric","level":5,"score":0.3221000134944916},{"id":"https://openalex.org/C48002344","wikidata":"https://www.wikidata.org/wiki/Q2919644","display_name":"Verification and validation","level":2,"score":0.31949999928474426},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30660000443458557},{"id":"https://openalex.org/C2776505523","wikidata":"https://www.wikidata.org/wiki/Q4785468","display_name":"Plan (archaeology)","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.2921999990940094},{"id":"https://openalex.org/C199521495","wikidata":"https://www.wikidata.org/wiki/Q181487","display_name":"Audit","level":2,"score":0.28839999437332153},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.28780001401901245},{"id":"https://openalex.org/C60048249","wikidata":"https://www.wikidata.org/wiki/Q37437","display_name":"Syntax","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.25450000166893005},{"id":"https://openalex.org/C21491501","wikidata":"https://www.wikidata.org/wiki/Q430253","display_name":"Backporting","level":5,"score":0.25040000677108765}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2611.03238","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03238","pdf_url":"https://arxiv.org/pdf/2611.03238","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.2611.03238","doi":"https://doi.org/10.48550/arxiv.2611.03238","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2611.03238","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:2611.03238","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2611.03238","pdf_url":"https://arxiv.org/pdf/2611.03238","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7151364916","https://openalex.org/W7126224745","https://openalex.org/W7133528385","https://openalex.org/W7204920322","https://openalex.org/W7206215664","https://openalex.org/W7211875777","https://openalex.org/W7215069900","https://openalex.org/W7167078648","https://openalex.org/W7117981194","https://openalex.org/W7221150091"],"abstract_inverted_index":{"Computer-use":[0],"agents":[1,242],"for":[2,94,112,159,240],"scientific":[3,245],"software":[4,16,38,70,224,246],"require":[5],"application-specific":[6],"expertise.":[7],"Much":[8],"of":[9,230],"this":[10],"expertise":[11],"is":[12],"documented":[13,35],"in":[14,42,134],"human-authored":[15],"manuals":[17],"and":[18,36,40,47,77,87,109,125,156,174,177,188,233,248],"web":[19],"pages.":[20],"However,":[21],"turning":[22],"these":[23],"resources":[24],"into":[25,80,226],"executable,":[26],"reusable":[27,81],"skills":[28,120,232],"remains":[29],"challenging":[30],"due":[31],"to":[32,102,197,215,243],"mismatches":[33],"between":[34,44],"deployed":[37],"versions":[39],"differences":[41],"scope":[43],"documentation":[45,225],"coverage":[46],"task":[48,145,161,192],"requirements.":[49],"We":[50],"introduce":[51,148],"ScienceCUA,":[52],"a":[53,237],"two-stage":[54],"framework":[55],"combining":[56],"resource-to-skill":[57],"construction":[58],"with":[59],"execution-guided":[60],"skill":[61,104,128,166,206],"evolution.":[62],"First,":[63],"ScienceCUA":[64,98,222],"identifies":[65],"tasks":[66,176],"supported":[67],"by":[68,106,195],"the":[69,113,127,185,202,209,213],"from":[71,168],"its":[72],"documentation,":[73],"infers":[74],"operational":[75],"trajectories,":[76],"generalizes":[78],"them":[79],"Skills.":[82],"Command":[83],"catalogs,":[84],"syntax":[85],"constraints,":[86],"shortcuts":[88],"are":[89],"organized":[90],"separately":[91],"as":[92,216,218],"References":[93,189],"on-demand":[95],"lookup.":[96],"Then,":[97],"uses":[99],"execution":[100],"feedback":[101],"drive":[103],"self-evolution":[105,207],"contrasting":[107],"successful":[108],"failed":[110],"trajectories":[111],"same":[114],"task,":[115],"identifying":[116],"deficiencies,":[117],"revising":[118],"existing":[119],"or":[121,144],"adding":[122],"new":[123],"ones,":[124],"updating":[126],"library":[129],"only":[130],"after":[131],"repeated":[132],"validation":[133],"real":[135],"environments.":[136],"To":[137],"enable":[138],"reliable":[139],"evaluation":[140],"without":[141],"benchmark":[142],"noise":[143],"leakage,":[146],"we":[147],"two":[149],"improved":[150],"benchmarks.":[151],"ScienceBoard-Verified":[152],"provides":[153],"an":[154,227],"audited":[155],"corrected":[157],"basis":[158],"measuring":[160],"performance,":[162],"while":[163,205],"ScienceBoard-VE":[164],"separates":[165],"evolution":[167,173],"final":[169],"testing":[170],"through":[171],"disjoint":[172],"test":[175],"further":[178],"supports":[179],"native-agent":[180],"evaluation.":[181],"Experiments":[182],"show":[183],"that":[184],"initial":[186],"Skills":[187],"improve":[190],"average":[191],"success":[193],"rate":[194],"up":[196],"7.23":[198],"percentage":[199,220],"points":[200],"over":[201,212],"base":[203],"model,":[204],"increases":[208],"total":[210],"gain":[211],"baseline":[214],"much":[217],"17.12":[219],"points.":[221],"turns":[223],"evolving":[228],"set":[229],"executable":[231],"queryable":[234],"references,":[235],"offering":[236],"practical":[238],"way":[239],"general-purpose":[241],"use":[244],"reliably":[247],"at":[249],"scale.":[250]},"counts_by_year":[],"updated_date":"2026-11-05T12:25:35.769452","created_date":"2026-11-04T00:00:00"}