The 8088 The 8088 ← All news
arXiv cs.AI AI Research Apr 22

AutomationBench

★★★★★ significance 3/5

The authors introduce AutomationBench, a new benchmark designed to evaluate AI agents on their ability to orchestrate complex workflows across multiple applications via REST APIs. The benchmark tests cross-application coordination, autonomous API discovery, and adherence to business policies, revealing that current frontier models score below 10% on these tasks.

Why it matters Standardizing how agents navigate complex, multi-app workflows is essential for moving beyond simple chat toward autonomous enterprise integration.
Read the original at arXiv cs.AI

Tags

#benchmarking #ai agents #automation #workflow orchestration #api

Related coverage