{"id":"https://openalex.org/W7204157766","doi":"https://doi.org/10.48550/arxiv.2608.23336","title":"Can Coding Agents Build Robust Baselines? A Skill-Based Approach for Automating the Medical Imaging Model-Development Pipeline","display_name":"Can Coding Agents Build Robust Baselines? A Skill-Based Approach for Automating the Medical Imaging Model-Development Pipeline","publication_year":2026,"publication_date":"2026-08-24","ids":{"openalex":"https://openalex.org/W7204157766","doi":"https://doi.org/10.48550/arxiv.2608.23336"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2608.23336","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23336","pdf_url":"https://arxiv.org/pdf/2608.23336","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/2608.23336","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058453097","display_name":"Eugenia Moris","orcid":"https://orcid.org/0000-0002-2982-1780","observed_orcids":["https://orcid.org/0000-0002-2982-1780"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Moris, Eugenia","raw_affiliation_strings":["Arionkoder LLC , Boston , MA 02114 , United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arionkoder LLC , Boston , MA 02114 , United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054255365","display_name":"Jos\u00e9 Ignacio Orlando","orcid":"https://orcid.org/0000-0001-9734-5571","observed_orcids":["https://orcid.org/0000-0001-9734-5571"]},"institutions":[{"id":"https://openalex.org/I3130805194","display_name":"Universidad Nacional del Centro de la Provincia de Buenos Aires","ror":"https://ror.org/011gakh74","country_code":"AR","type":"education","lineage":["https://openalex.org/I3130805194"]}],"countries":["AR"],"is_corresponding":false,"raw_author_name":"Orlando, Jos\u00e9 Ignacio","raw_affiliation_strings":["Arionkoder LLC , Boston , MA 02114 , United States","Yatiris , PLADEMA , UNICEN-CONICET , Tandil , Buenos Aires , Argentina"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arionkoder LLC , Boston , MA 02114 , United States","institution_ids":[]},{"raw_affiliation_string":"Yatiris , PLADEMA , UNICEN-CONICET , Tandil , Buenos Aires , Argentina","institution_ids":["https://openalex.org/I3130805194"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.6542999744415283,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.6542999744415283,"subfield":{"id":"https://openalex.org/subfields/2718","display_name":"Health Informatics"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10052","display_name":"Medical Image Segmentation Techniques","score":0.18809999525547028,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10862","display_name":"AI in cancer detection","score":0.023800000548362732,"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/agentic-ai","display_name":"agentic AI","score":0.7559999823570251},{"id":"https://openalex.org/keywords/ai-scientists","display_name":"AI scientists","score":0.48100000619888306},{"id":"https://openalex.org/keywords/diagnostic-imaging","display_name":"diagnostic imaging","score":0.6890000104904175},{"id":"https://openalex.org/keywords/automatic-code-generation","display_name":"automatic code generation","score":0.8399999737739563},{"id":"https://openalex.org/keywords/medical-image-segmentation","display_name":"medical image segmentation","score":0.6970000267028809},{"id":"https://openalex.org/keywords/medical-image-classification","display_name":"medical image classification","score":0.9670000076293945},{"id":"https://openalex.org/keywords/medical-image-detection","display_name":"medical image detection","score":0.9300000071525574},{"id":"https://openalex.org/keywords/domain-generalization","display_name":"domain generalization","score":0.847000002861023},{"id":"https://openalex.org/keywords/puma","display_name":"PUMA","score":0.5580000281333923}],"concepts":[{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.838100016117096},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7103999853134155},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5990999937057495},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5414000153541565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5078999996185303},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.5060999989509583},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5011000037193298},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.48249998688697815},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4823000133037567},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.45890000462532043},{"id":"https://openalex.org/C143587482","wikidata":"https://www.wikidata.org/wiki/Q1543216","display_name":"Iterative and incremental development","level":2,"score":0.4447000026702881},{"id":"https://openalex.org/C534262118","wikidata":"https://www.wikidata.org/wiki/Q177719","display_name":"Medical diagnosis","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C31601959","wikidata":"https://www.wikidata.org/wiki/Q931309","display_name":"Medical imaging","level":2,"score":0.4180000126361847},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.4049000144004822},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.34130001068115234},{"id":"https://openalex.org/C105002631","wikidata":"https://www.wikidata.org/wiki/Q4833645","display_name":"Subject-matter expert","level":3,"score":0.32829999923706055},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.32519999146461487},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.32420000433921814},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.31439998745918274},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.29019999504089355},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.27869999408721924},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.2565000057220459}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2608.23336","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23336","pdf_url":"https://arxiv.org/pdf/2608.23336","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2608.23336","doi":"https://doi.org/10.48550/arxiv.2608.23336","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2608.23336","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":"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2608.23336","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2608.23336","pdf_url":"https://arxiv.org/pdf/2608.23336","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7204157766.pdf","grobid_xml":"https://content.openalex.org/works/W7204157766.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W4378505261","https://openalex.org/W4393065402","https://openalex.org/W4402952666","https://openalex.org/W4406231153"],"related_works":["https://openalex.org/W7223148840","https://openalex.org/W7168250390","https://openalex.org/W7110980984","https://openalex.org/W4414826971","https://openalex.org/W6966854973","https://openalex.org/W7204894076","https://openalex.org/W4414421921","https://openalex.org/W7116978705","https://openalex.org/W7163140972","https://openalex.org/W7213370950"],"abstract_inverted_index":{"Developing":[0],"competitive":[1,61,92,153],"deep":[2],"learning":[3],"baselines":[4],"for":[5,64],"medical":[6,65,154],"imaging":[7,66,155],"remains":[8],"a":[9],"highly":[10],"iterative":[11],"process":[12],"requiring":[13],"literature":[14],"review,":[15],"implementation,":[16],"experimentation,":[17],"and":[18,56,79,104,125],"expert":[19],"refinement.":[20],"Existing":[21],"automation":[22],"approaches":[23],"typically":[24],"optimize":[25],"isolated":[26],"components,":[27],"such":[28],"as":[29],"architecture":[30],"search":[31],"or":[32],"hyperparameter":[33],"tuning,":[34],"rather":[35],"than":[36],"the":[37,84,113,128,147],"complete":[38],"baseline":[39,62],"development":[40],"process.":[41],"We":[42],"present":[43],"an":[44],"agentic":[45,142],"AI":[46],"Scientist":[47],"workflow":[48,130],"that":[49,139],"combines":[50],"literature-guided":[51,141],"reasoning,":[52],"automated":[53],"code":[54],"generation,":[55],"hypothesis-driven":[57],"experimentation":[58],"to":[59,151],"generate":[60],"models":[63],"challenges.":[67],"The":[68],"framework":[69],"is":[70],"evaluated":[71],"on":[72,98,107],"four":[73],"public":[74],"benchmarks":[75],"spanning":[76],"segmentation,":[77],"classification,":[78],"detection.":[80],"Across":[81],"all":[82,132],"tasks,":[83],"Experimentation":[85],"Pipeline":[86],"consistently":[87],"improves":[88],"validation":[89],"performance,":[90],"achieving":[91],"leaderboard":[93],"results,":[94],"including":[95],"6th":[96],"place":[97,106],"both":[99],"PUMA":[100],"tracks":[101],"(15":[102],"teams)":[103],"31st":[105],"MILK10k":[108],"(125":[109],"teams).":[110],"On":[111],"MIDOG25,":[112],"resulting":[114],"model":[115],"also":[116],"demonstrates":[117],"strong":[118],"domain":[119],"generalization":[120],"across":[121,131],"scanners,":[122],"tumor":[123],"types,":[124],"species.":[126],"Using":[127],"same":[129],"challenges":[133],"without":[134],"task-specific":[135],"redesign,":[136],"we":[137],"demonstrate":[138],"skill-based,":[140],"workflows":[143],"can":[144],"substantially":[145],"reduce":[146],"engineering":[148],"effort":[149],"required":[150],"develop":[152],"baselines.":[156]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-08-26T00:00:00"}