{"id":"https://openalex.org/W7224823517","doi":"https://doi.org/10.48550/arxiv.2610.39733","title":"Bank-World: A Benchmark for Evaluating Agents on Banking Workflows","display_name":"Bank-World: A Benchmark for Evaluating Agents on Banking Workflows","publication_year":2026,"publication_date":"2026-10-29","ids":{"openalex":"https://openalex.org/W7224823517","doi":"https://doi.org/10.48550/arxiv.2610.39733"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2610.39733","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39733","pdf_url":"https://arxiv.org/pdf/2610.39733","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","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2610.39733","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5160230421","display_name":"Daniel Rupawalla","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Rupawalla, Daniel","raw_affiliation_strings":["Arcanum Labs"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arcanum Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5160230421"],"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.34060001373291016,"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":0.34060001373291016,"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/T13904","display_name":"Artificial Intelligence Applications","score":0.17520000040531158,"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/T12031","display_name":"Speech and dialogue systems","score":0.04800000041723251,"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/llm-based-agents","display_name":"LLM agents","score":0.5929999947547913},{"id":"https://openalex.org/keywords/benchmark","display_name":"benchmark","score":0.5450000166893005},{"id":"https://openalex.org/keywords/multi-turn-interaction","display_name":"multi-turn interaction","score":0.6320000290870667},{"id":"https://openalex.org/keywords/task-completion","display_name":"task completion","score":0.5289999842643738},{"id":"https://openalex.org/keywords/agent-evaluation","display_name":"agent evaluation","score":0.5590000152587891},{"id":"https://openalex.org/keywords/worked-examples","display_name":"worked examples","score":0.7369999885559082}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8169000148773193},{"id":"https://openalex.org/C160145156","wikidata":"https://www.wikidata.org/wiki/Q778586","display_name":"Executable","level":2,"score":0.7904000282287598},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.7253000140190125},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6689000129699707},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6237999796867371},{"id":"https://openalex.org/C145097563","wikidata":"https://www.wikidata.org/wiki/Q1148747","display_name":"Payment","level":2,"score":0.5627999901771545},{"id":"https://openalex.org/C2777286243","wikidata":"https://www.wikidata.org/wiki/Q5591926","display_name":"Grading (engineering)","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4595000147819519},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.3483000099658966},{"id":"https://openalex.org/C42475967","wikidata":"https://www.wikidata.org/wiki/Q194292","display_name":"Operations research","level":1,"score":0.32429999113082886},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.28290000557899475},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2660999894142151},{"id":"https://openalex.org/C2780069185","wikidata":"https://www.wikidata.org/wiki/Q7977945","display_name":"Equivalence (formal languages)","level":2,"score":0.2637999951839447},{"id":"https://openalex.org/C29122968","wikidata":"https://www.wikidata.org/wiki/Q1414816","display_name":"Incentive","level":2,"score":0.2540000081062317},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.25360000133514404},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.251800000667572}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2610.39733","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39733","pdf_url":"https://arxiv.org/pdf/2610.39733","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.2610.39733","doi":"https://doi.org/10.48550/arxiv.2610.39733","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2610.39733","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:2610.39733","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2610.39733","pdf_url":"https://arxiv.org/pdf/2610.39733","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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7224823517.pdf","grobid_xml":"https://content.openalex.org/works/W7224823517.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7154374450","https://openalex.org/W7156608054","https://openalex.org/W4396653533","https://openalex.org/W2785582641","https://openalex.org/W7165666907","https://openalex.org/W7162067644","https://openalex.org/W7206175763","https://openalex.org/W7166834168","https://openalex.org/W7208748326","https://openalex.org/W7223700031"],"abstract_inverted_index":{"Bank-World":[0,40,147],"is":[1,119],"a":[2],"benchmark":[3,183],"of":[4,65,73],"50":[5],"banking":[6,13],"tasks":[7,143],"across":[8,140],"two":[9],"simulated":[10,51,164],"institutions.":[11],"Completing":[12],"work":[14],"requires":[15],"more":[16,141],"than":[17],"producing":[18],"the":[19,105,112,131,168,182],"right":[20],"calculation:":[21],"agents":[22],"must":[23],"reconcile":[24],"records,":[25],"obtain":[26],"permission,":[27],"execute":[28,115],"transactions,":[29],"and":[30,33,47,58,68,114,137,155,163,173,180],"keep":[31],"instructions":[32],"status":[34],"reports":[35],"consistent":[36],"as":[37],"circumstances":[38],"change.":[39],"tests":[41],"these":[42,149],"requirements":[43],"through":[44,152],"single-turn":[45,127],"assignments":[46],"multi-turn":[48,134,142],"interactions":[49],"with":[50,70],"employees":[52],"who":[53],"supply":[54],"information,":[55],"approve":[56],"actions,":[57],"revise":[59],"instructions.":[60],"Grading":[61],"combines":[62],"executable":[63,171],"checks":[64],"recorded":[66],"actions":[67],"state":[69],"model":[71],"judgments":[72],"task":[74,169],"requirements,":[75],"including":[76],"whether":[77],"valid":[78],"alternative":[79],"solutions":[80],"satisfy":[81],"them.":[82],"Across":[83],"1,600":[84],"attempts":[85],"by":[86],"four":[87],"models,":[88],"we":[89],"find":[90],"that":[91],"correct":[92,106],"decisions":[93],"often":[94],"fail":[95],"to":[96,177],"become":[97],"completed":[98],"work.":[99],"Agents":[100],"charge":[101],"fees":[102],"twice,":[103],"distribute":[104],"total":[107],"in":[108],"incorrect":[109],"amounts":[110],"among":[111],"recipients,":[113],"payments":[116],"while":[117],"approval":[118],"pending.":[120],"Their":[121],"strengths":[122],"also":[123],"differ:":[124],"Sol":[125],"leads":[126],"completion,":[128],"Opus":[129],"has":[130],"highest":[132],"observed":[133],"completion":[135],"rate,":[136],"Grok":[138],"succeeds":[139],"but":[144],"less":[145],"consistently.":[146],"makes":[148],"differences":[150],"inspectable":[151],"task-level":[153],"results":[154],"worked":[156],"examples":[157],"connecting":[158],"source":[159],"evidence,":[160],"agent":[161],"decisions,":[162],"consequences.":[165],"We":[166],"retain":[167],"environments,":[170],"graders,":[172],"full":[174],"trajectories":[175],"privately":[176],"reduce":[178],"contamination":[179],"preserve":[181],"for":[184],"future":[185],"evaluations.":[186]},"counts_by_year":[],"updated_date":"2026-11-06T12:05:46.655746","created_date":"2026-10-31T00:00:00"}