APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces

APEX-Harm: Evaluating Agent Safety in Shared Professional Workspaces. It centres on Benchmarks, and also names Model Context Protocol and Gemini. Reported by arXiv. Bharat Hunt files it under AI Models and AI Agents — the section covering a new or updated model, its capabilities, benchmarks or availability.

Written by Bharat Hunt from the headline and the coverage below. The original reporting is the source of truth.