runtime-contract

Tag

Cards List
#runtime-contract

Agent Safety Should Be a Runtime Contract

Hugging Face Daily Papers · 4d ago Cached

This paper argues that AI agent safety should be enforced at runtime via preventive controls and verifiable evidence, rather than relying solely on training-time alignment. It grounds the position in audits of safety incidents, false completions, trajectory schemas, and publication trends.

0 favorites 0 likes
← Back to home

Submit Feedback