2 papers
cs.CY2026
Safety Degradation in AI Agents
Cheng Yu, Benedikt Stroebl, Diyi Yang +1
Despite the growing integration of retrieval-enabled AI agents into society, their safety and ethical behavior remain inadequately understood. In particular, the integration of LLM…
cs.CY2026
How Should AI Safety Benchmarks Benchmark Safety?
Cheng Yu, Severin Engelmann, Ruoxuan Cao +2
AI safety benchmarks are pivotal for safety in advanced AI systems; however, they have significant technical, epistemic, and sociotechnical shortcomings. We present a review of 210…