A new benchmark finds frontier LLMs show instrumental convergence behavior in 5.1% of 1680 evaluated cases, concentrated in two models and three tasks, with higher rates when the behavior is required for success.
Can AI agents escape their sandboxes? A benchmark for safely measuring container breakout capabilities | AISI Work
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Instrumental Choices: Measuring the Propensity of LLM Agents to Pursue Instrumental Behaviors
A new benchmark finds frontier LLMs show instrumental convergence behavior in 5.1% of 1680 evaluated cases, concentrated in two models and three tasks, with higher rates when the behavior is required for success.