LinuxArena

Search everything

Mentions · 7d0
Mentions · 30d1
All mentions1
First seenOct 15, 2026
Last mentioned10d ago

Timeline

1 articles · newest first

Shortcut Sensitivity in Agent-Safety Evaluations

Shortcut cues in agent-safety benchmarks can change guard decisions and measured accuracy.

arXiv cs.CROct 15, 17:18 UTC · 10d agoAI safety & security9 · 5 reads

Appears with

TS-Guardproduct · 1
AgentHarmproduct · 1
Haikuai model · 1
AgentDojoproduct · 1

Entities are extracted by the model from each article. First seen Oct 15, 2026, last mentioned 10d ago. Watching keeps it in this browser only (no account); the watchlist page and dashboard alerts use it.