Guardado en:
| Autores principales: | , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2604.18934 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910152628633600 |
|---|---|
| author | Shepard, Daniel Salimans, Robin |
| author_facet | Shepard, Daniel Salimans, Robin |
| contents | Existing AI benchmarks for software automation rarely combine cross-application coordination, autonomous API discovery, and policy adherence. Real business workflows demand all three: a single task may span a CRM, inbox, calendar, and messaging platform - requiring the agent to find the right endpoints, follow a policy document, and write correct data to each system. To address this gap, we introduce AutomationBench, a benchmark for evaluating AI agents on cross-application workflow orchestration via REST APIs. Drawing on real workflow patterns from Zapier's platform, tasks span Sales, Marketing, Operations, Support, Finance, and HR domains. Agents must discover relevant endpoints themselves, follow layered business rules, and navigate environments with irrelevant and sometimes misleading records. Grading is programmatic and end-state only: whether the correct data ended up in the right systems. Even the best frontier models currently score below 10%. AutomationBench provides a challenging, realistic measure of where current models stand relative to the agentic capabilities businesses actually need. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_18934 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AutomationBench Shepard, Daniel Salimans, Robin Artificial Intelligence Existing AI benchmarks for software automation rarely combine cross-application coordination, autonomous API discovery, and policy adherence. Real business workflows demand all three: a single task may span a CRM, inbox, calendar, and messaging platform - requiring the agent to find the right endpoints, follow a policy document, and write correct data to each system. To address this gap, we introduce AutomationBench, a benchmark for evaluating AI agents on cross-application workflow orchestration via REST APIs. Drawing on real workflow patterns from Zapier's platform, tasks span Sales, Marketing, Operations, Support, Finance, and HR domains. Agents must discover relevant endpoints themselves, follow layered business rules, and navigate environments with irrelevant and sometimes misleading records. Grading is programmatic and end-state only: whether the correct data ended up in the right systems. Even the best frontier models currently score below 10%. AutomationBench provides a challenging, realistic measure of where current models stand relative to the agentic capabilities businesses actually need. |
| title | AutomationBench |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2604.18934 |