Showing cs.AIShow all
3 papers · 1 filter
cs.AI2026
Attack Selection in Agentic AI Control Evaluations Meaningfully Decreases Safety
Catherine Ge-Wang, Tyler Crosse, Benjamin Hadad +3
An attacker that strategically chooses when to attack is much harder to catch than one that attacks indiscriminately. AI control is a safety framework for deploying capable but unt…
cs.AI2026
Asymmetric Goal Drift in Coding Agents Under Value Conflict
Magnus Saebo, Spencer Gibson, Tyler Crosse +3
Coding agents are increasingly deployed autonomously, at scale, and over long-context horizons. To be effective and safe, these agents must navigate complex trade-offs in deploymen…
cs.AI2026
Inherited Goal Drift: Contextual Pressure Can Undermine Agentic Goals
Achyutha Menon, Magnus Saebo, Tyler Crosse +3
The accelerating adoption of language models (LMs) as agents for deployment in long-context tasks motivates a thorough understanding of goal drift: agents' tendency to deviate from…