{"id":"https://openalex.org/W7214743407","doi":"https://doi.org/10.48550/arxiv.2609.34274","title":"BIABench: Evaluating AI agents on real-world bioimage analysis tasks","display_name":"BIABench: Evaluating AI agents on real-world bioimage analysis tasks","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214743407","doi":"https://doi.org/10.48550/arxiv.2609.34274"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2609.34274","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34274","pdf_url":"https://arxiv.org/pdf/2609.34274","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/2609.34274","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101381217","display_name":"Zixuan Pan","orcid":"https://orcid.org/0000-0003-0177-1520","observed_orcids":["https://orcid.org/0000-0003-0177-1520"]},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pan, Zixuan","raw_affiliation_strings":["Department of Computer Science and Engineering , University of Notre Dame , Notre Dame , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Notre Dame , Notre Dame , USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101566234","display_name":"Davide Panzeri","orcid":"https://orcid.org/0009-0000-8773-5883","observed_orcids":["https://orcid.org/0009-0000-8773-5883"]},"institutions":[{"id":"https://openalex.org/I4210121365","display_name":"Leibniz Institute for Analytical Sciences - ISAS","ror":"https://ror.org/02jhqqg57","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210121365"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Panzeri, Davide","raw_affiliation_strings":["Leibniz-Institut f\u00fcr Analytische Wissenschaften -ISAS -e.V. , Dortmund , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz-Institut f\u00fcr Analytische Wissenschaften -ISAS -e.V. , Dortmund , Germany","institution_ids":["https://openalex.org/I4210121365"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5130986988","display_name":"Lukas Johanns","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210121365","display_name":"Leibniz Institute for Analytical Sciences - ISAS","ror":"https://ror.org/02jhqqg57","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210121365"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johanns, Lukas","raw_affiliation_strings":["Leibniz-Institut f\u00fcr Analytische Wissenschaften -ISAS -e.V. , Dortmund , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz-Institut f\u00fcr Analytische Wissenschaften -ISAS -e.V. , Dortmund , Germany","institution_ids":["https://openalex.org/I4210121365"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5137374001","display_name":"Marilin Moor","orcid":"https://orcid.org/0009-0006-1964-5388","observed_orcids":["https://orcid.org/0009-0006-1964-5388"]},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Moor, Marilin","raw_affiliation_strings":["Institute of Computer Science , University of Tartu , Tartu , Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science , University of Tartu , Tartu , Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153460914","display_name":"Yu Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210121365","display_name":"Leibniz Institute for Analytical Sciences - ISAS","ror":"https://ror.org/02jhqqg57","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210121365"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Zhou, Yu","raw_affiliation_strings":["Leibniz-Institut f\u00fcr Analytische Wissenschaften -ISAS -e.V. , Dortmund , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz-Institut f\u00fcr Analytische Wissenschaften -ISAS -e.V. , Dortmund , Germany","institution_ids":["https://openalex.org/I4210121365"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089890429","display_name":"Hedi Peterson","orcid":"https://orcid.org/0000-0001-9951-5116","observed_orcids":["https://orcid.org/0000-0001-9951-5116"]},"institutions":[{"id":"https://openalex.org/I56085075","display_name":"University of Tartu","ror":"https://ror.org/03z77qz90","country_code":"EE","type":"education","lineage":["https://openalex.org/I56085075"]}],"countries":["EE"],"is_corresponding":false,"raw_author_name":"Peterson, Hedi","raw_affiliation_strings":["Institute of Computer Science , University of Tartu , Tartu , Estonia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Computer Science , University of Tartu , Tartu , Estonia","institution_ids":["https://openalex.org/I56085075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5153452454","display_name":"Yiyu Shi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I107639228","display_name":"University of Notre Dame","ror":"https://ror.org/00mkhxb43","country_code":"US","type":"education","lineage":["https://openalex.org/I107639228"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shi, Yiyu","raw_affiliation_strings":["Department of Computer Science and Engineering , University of Notre Dame , Notre Dame , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering , University of Notre Dame , Notre Dame , USA","institution_ids":["https://openalex.org/I107639228"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5153485369","display_name":"Jianxu Chen","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210121365","display_name":"Leibniz Institute for Analytical Sciences - ISAS","ror":"https://ror.org/02jhqqg57","country_code":"DE","type":"facility","lineage":["https://openalex.org/I315704651","https://openalex.org/I4210121365"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Chen, Jianxu","raw_affiliation_strings":["Leibniz-Institut f\u00fcr Analytische Wissenschaften -ISAS -e.V. , Dortmund , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz-Institut f\u00fcr Analytische Wissenschaften -ISAS -e.V. , Dortmund , Germany","institution_ids":["https://openalex.org/I4210121365"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12859","display_name":"Cell Image Analysis Techniques","score":0.9810000061988831,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.006200000178068876,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.0020000000949949026,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-agents","display_name":"AI agents","score":0.8640000224113464},{"id":"https://openalex.org/keywords/bioimage-analysis","display_name":"bioimage analysis","score":0.984000027179718},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.9010000228881836},{"id":"https://openalex.org/keywords/vision-language-models","display_name":"vision-language models","score":0.7670000195503235},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.6169999837875366},{"id":"https://openalex.org/keywords/h-e-histology","display_name":"H&E histology","score":0.6899999976158142},{"id":"https://openalex.org/keywords/single-molecule-localization-microscopy","display_name":"single-molecule localization microscopy","score":0.9739999771118164},{"id":"https://openalex.org/keywords/3d-image-analysis","display_name":"3D image analysis","score":0.7630000114440918},{"id":"https://openalex.org/keywords/time-lapse-imaging","display_name":"time-lapse imaging","score":0.8809999823570251},{"id":"https://openalex.org/keywords/ground-truth","display_name":"ground truth","score":0.45399999618530273},{"id":"https://openalex.org/keywords/agent-reliability","display_name":"agent reliability","score":0.5410000085830688}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7623999714851379},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7610999941825867},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.6620000004768372},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5809999704360962},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5615000128746033},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.51419997215271},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4551999866962433},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4514999985694885},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4309999942779541},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.38190001249313354},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3497999906539917},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.32710000872612},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.302700012922287},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.29679998755455017},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.2919999957084656},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27549999952316284},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.25}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2609.34274","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34274","pdf_url":"https://arxiv.org/pdf/2609.34274","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.2609.34274","doi":"https://doi.org/10.48550/arxiv.2609.34274","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2609.34274","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:2609.34274","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2609.34274","pdf_url":"https://arxiv.org/pdf/2609.34274","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/G4852436649","display_name":"Estonian Life Science Infrastructure","funder_award_id":"TARISTU24-TK4","funder_id":"https://openalex.org/F4320321090","funder_display_name":"Eesti Teadusagentuur"},{"id":"https://openalex.org/G519341576","display_name":"NFDI4BIOIMAGE  Nationale Forschungsdateninfrastruktur f\u00fcr Mikroskopie und Bildanalyse","funder_award_id":"501864659","funder_id":"https://openalex.org/F4320320879","funder_display_name":"Deutsche Forschungsgemeinschaft"}],"funders":[{"id":"https://openalex.org/F4320320879","display_name":"Deutsche Forschungsgemeinschaft","ror":"https://ror.org/018mejw64"},{"id":"https://openalex.org/F4320321090","display_name":"Eesti Teadusagentuur","ror":"https://ror.org/00jjeja18"},{"id":"https://openalex.org/F4320324717","display_name":"Tartu \u00dclikool","ror":"https://ror.org/03z77qz90"},{"id":"https://openalex.org/F4320328599","display_name":"Ministerium f\u00fcr Kultur und Wissenschaft des Landes Nordrhein-Westfalen","ror":null}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214743407.pdf","grobid_xml":"https://content.openalex.org/works/W7214743407.grobid-xml"},"referenced_works_count":16,"referenced_works":["https://openalex.org/W4394986684","https://openalex.org/W4402345509","https://openalex.org/W4414028042","https://openalex.org/W4417089504","https://openalex.org/W4417136556","https://openalex.org/W6904688922","https://openalex.org/W6948174282","https://openalex.org/W6948306691","https://openalex.org/W6968484951","https://openalex.org/W7160715433","https://openalex.org/W7161178917","https://openalex.org/W7162690279","https://openalex.org/W7163129786","https://openalex.org/W7164437655","https://openalex.org/W7203751154","https://openalex.org/W7204493988"],"related_works":["https://openalex.org/W7204493988","https://openalex.org/W7222754646","https://openalex.org/W7126207648","https://openalex.org/W7160715433","https://openalex.org/W7163129786","https://openalex.org/W4414028042","https://openalex.org/W7161178917","https://openalex.org/W7162627714","https://openalex.org/W7133791153","https://openalex.org/W7117532729"],"abstract_inverted_index":{"Artificial-intelligence":[0],"(AI)":[1],"agents":[2,28,156,204,263],"hold":[3],"promise":[4],"for":[5,27,258,264],"automating":[6],"bioimage":[7,267],"analysis,":[8],"yet":[9],"no":[10,186],"benchmark":[11,80],"evaluates":[12],"whether":[13],"they":[14],"can":[15],"carry":[16],"out":[17],"real-world":[18],"analyses":[19,24],"end":[20],"to":[21,41,110],"end.":[22],"Such":[23],"are":[25,37],"hard":[26],"because":[29,67],"2D":[30],"images,":[31],"3D":[32],"volumes":[33],"and":[34,50,58,96,105,132,144,154,222,251,260],"time-lapse":[35],"sequences":[36],"often":[38],"too":[39],"large":[40],"read":[42],"as":[43],"context,":[44],"so":[45],"an":[46,52,117,148],"agent":[47,187,217],"must":[48],"choose":[49],"run":[51,228],"analysis":[53,103],"through":[54],"code,":[55,252],"specialized":[56],"software":[57],"rendered":[59],"views.":[60],"Published":[61],"studies":[62,88],"make":[63],"this":[64,201],"capability":[65],"testable,":[66],"each":[68],"pairs":[69],"raw":[70],"images":[71],"with":[72,125,161,208,248],"a":[73,79,133,138,179,183,226,234,255],"peer-reviewed":[74],"result.":[75],"We":[76,151],"introduce":[77],"BIABench,":[78],"of":[81,164,215],"16":[82],"tasks":[83,100,169,176],"reconstructed":[84],"from":[85,107,233],"published":[86],"biological":[87,192],"that":[89,177],"retain":[90],"their":[91],"scientific":[92],"questions,":[93],"imaging":[94],"data":[95,250],"ground":[97,127,224],"truth.":[98],"The":[99,203],"span":[101],"eleven":[102],"subtasks":[104],"modalities":[106],"H&E":[108],"histology":[109],"single-molecule":[111],"localization":[112],"microscopy.":[113],"Each":[114],"submission":[115],"receives":[116],"outcome":[118],"score,":[119,135],"which":[120,137],"compares":[121],"the":[122,126,243],"output":[123],"files":[124],"truth":[128,225],"using":[129],"field-standard":[130],"metrics,":[131],"process":[134,239],"in":[136],"vision-language":[139],"model":[140],"judges":[141],"method":[142],"choice":[143],"quality":[145],"control":[146],"against":[147],"expert-written":[149],"rubric.":[150],"evaluated":[152],"general-purpose":[153],"biology-specific":[155],"across":[157],"several":[158],"language":[159],"models,":[160],"repeated":[162,213],"runs":[163,214],"every":[165],"task.":[166],"Routine":[167],"two-dimensional":[168],"were":[170,205],"solved":[171],"well,":[172],"but":[173],"on":[174],"some":[175],"added":[178],"third":[180],"dimension":[181],"or":[182,241],"time":[184,244],"axis":[185],"scored":[188],"above":[189],"0.19.":[190],"Neither":[191],"specialization,":[193],"stronger":[194],"models":[195],"nor":[196],"detailed":[197],"expert":[198],"instructions":[199],"closed":[200],"gap.":[202],"also":[206],"unreliable,":[207],"scores":[209],"varying":[210],"more":[211],"between":[212,219],"one":[216,236],"than":[218],"different":[220],"agents,":[221],"without":[223],"correct":[227],"could":[229],"not":[230],"be":[231],"told":[232],"wrong":[235],"by":[237,242],"its":[238,249],"score":[240],"spent.":[245],"Released":[246],"openly":[247],"BIABench":[253],"provides":[254],"verifiable":[256],"framework":[257],"evaluating,":[259],"eventually":[261],"training,":[262],"reliable":[265],"long-horizon":[266],"analysis.":[268]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2026-09-30T00:00:00"}