SOURCE-LINKED INTELLIGENCE

Rare Event Estimation via Iterative Unalignment

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

As agents are deployed with increased autonomy, even extremely rare events along their stochastic output trajectories can occur and prove catastrophic. Safe deployment therefore does not depend on whether these events can occur, but on how often they might. We study the problem of estimating the probability of rare events that arise from stochastic variation in the agent's own actions. Estimating this type of risk requires searching over the combinatorially vast space of trajectories. Naive Monte Carlo is computationally prohibitive in this regime, and constructing effective importance samplin

Read original source ↗ Open in workspace

recordType

paper

region

Global