{"id":"https://openalex.org/W7126207648","doi":"https://doi.org/10.48550/arxiv.2601.21800","title":"BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics","display_name":"BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics","publication_year":2026,"publication_date":"2026-01-29","ids":{"openalex":"https://openalex.org/W7126207648","doi":"https://doi.org/10.48550/arxiv.2601.21800"},"language":null,"primary_location":{"id":"pmh:oai:arXiv.org:2601.21800","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.21800","pdf_url":"https://arxiv.org/pdf/2601.21800","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.21800","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5059599646","display_name":"Dionizije Fa","orcid":"https://orcid.org/0009-0004-9909-0145","observed_orcids":["https://orcid.org/0009-0004-9909-0145"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fa, Dionizije","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023341808","display_name":"Marko \u010culjak","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Culjak, Marko","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124306938","display_name":"Bruno Pand\u017ea","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Pandza, Bruno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5124452900","display_name":"Mateo \u010cupi\u0107","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cupic, Mateo","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":true,"cited_by_count":2,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9731000065803528,"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"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9731000065803528,"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"}},{"id":"https://openalex.org/T13904","display_name":"Artificial Intelligence Applications","score":0.005799999926239252,"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/T11636","display_name":"Artificial Intelligence in Healthcare and Education","score":0.0038999998942017555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/ai-agent-evaluation","display_name":"AI agent evaluation","score":0.9210000038146973},{"id":"https://openalex.org/keywords/bioinformatics-pipeline","display_name":"bioinformatics pipeline","score":0.7020000219345093},{"id":"https://openalex.org/keywords/large-language-models","display_name":"large language models","score":0.8180000185966492},{"id":"https://openalex.org/keywords/prompt-engineering","display_name":"prompt engineering","score":0.5879999995231628},{"id":"https://openalex.org/keywords/robustness-testing","display_name":"robustness testing","score":0.6650000214576721},{"id":"https://openalex.org/keywords/rna-seq","display_name":"RNA-seq","score":0.6439999938011169},{"id":"https://openalex.org/keywords/variant-calling","display_name":"variant calling","score":0.9990000128746033},{"id":"https://openalex.org/keywords/metagenomics","display_name":"metagenomics","score":0.9990000128746033},{"id":"https://openalex.org/keywords/multi-step-reasoning","display_name":"multi-step reasoning","score":0.5410000085830688},{"id":"https://openalex.org/keywords/local-agents","display_name":"local agents","score":0.44200000166893005},{"id":"https://openalex.org/keywords/automated-assessment","display_name":"automated assessment","score":0.382999986410141}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7885000109672546},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.7738000154495239},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7520999908447266},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6001999974250793},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5975000262260437},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5914000272750854},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4250999987125397},{"id":"https://openalex.org/C151552104","wikidata":"https://www.wikidata.org/wiki/Q7705809","display_name":"Test suite","level":4,"score":0.36559998989105225},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.29100000858306885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26589998602867126},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2653000056743622},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2632000148296356},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2603999972343445},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2547999918460846}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.21800","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.21800","pdf_url":"https://arxiv.org/pdf/2601.21800","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.2601.21800","doi":"https://doi.org/10.48550/arxiv.2601.21800","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.21800","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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.21800","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.21800","pdf_url":"https://arxiv.org/pdf/2601.21800","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":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7126207648.pdf","grobid_xml":"https://content.openalex.org/works/W7126207648.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"We":[0,46,69],"introduce":[1],"BioAgent":[2],"Bench,":[3],"an":[4,59],"evaluation":[5],"suite":[6,22],"designed":[7],"for":[8],"measuring":[9],"the":[10,88,123,126,138],"performance":[11],"and":[12,38,50,57,66,106,125],"robustness":[13,94],"of":[14,24,140,147],"AI":[15],"agents":[16,72],"in":[17],"common":[18],"bioinformatics":[19,80,150],"tasks.":[20],"The":[21],"consists":[23],"manually":[25],"curated":[26],"end-to-end":[27],"tasks":[28],"(e.g.,":[29],"RNA-seq,":[30],"variant":[31],"calling,":[32],"metagenomics)":[33],"accompanied":[34],"by":[35],"task-specific":[36],"prompts":[37],"concrete":[39],"output":[40],"artifacts":[41,91],"to":[42,62,136],"support":[43],"automated":[44],"assessment.":[45],"evaluate":[47],"frontier":[48,75],"closed-":[49],"open-weight":[51],"models":[52],"across":[53],"multiple":[54],"agent":[55],"harnesses,":[56],"use":[58],"LLM-based":[60],"grader":[61],"score":[63],"pipeline":[64,113],"progress":[65],"outcome":[67],"validity.":[68],"find":[70],"that":[71,110],"based":[73],"on":[74],"LLMs":[76],"can":[77],"complete":[78],"multi-step":[79],"pipelines":[81],"without":[82],"elaborate":[83],"custom":[84],"scaffolding,":[85],"often":[86,152],"producing":[87],"requested":[89],"final":[90],"reliably.":[92],"However,":[93],"tests":[95],"reveal":[96],"failure":[97],"modes":[98],"under":[99],"controlled":[100],"perturbations":[101],"(corrupted":[102],"inputs,":[103],"decoy":[104],"files,":[105],"prompt":[107],"bloat),":[108],"indicating":[109],"correct":[111],"high-level":[112],"construction":[114],"does":[115],"not":[116],"guarantee":[117],"reliable":[118,143],"step-level":[119],"reasoning.":[120],"By":[121],"releasing":[122],"code":[124],"complementary":[127],"resources":[128],"constituting":[129],"our":[130,132],"suite,":[131],"primary":[133],"goal":[134],"is":[135],"accelerate":[137],"development":[139],"cost-effective":[141],"yet":[142],"local":[144],"agents,":[145],"capable":[146],"handling":[148],"complex":[149],"workflows":[151],"involving":[153],"sensitive":[154],"patient":[155],"data":[156],"or":[157],"unpublished":[158],"intellectual":[159],"property.":[160]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-10-20T09:52:01.089006","created_date":"2026-02-01T00:00:00"}