AutomationBench is a new benchmark for AI agents on cross-application REST API workflows where even top models score below 10%.
Quarterly prod- uct review with partners
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AutomationBench
AutomationBench is a new benchmark for AI agents on cross-application REST API workflows where even top models score below 10%.