DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model

As large language model (LLM) agents increasingly invoke external tools and interact with real-world systems, unsafe actions may cause irreversible consequences on external states, user data, and downstream services. Recent runtime guardrails mitigate such risks by checking proposed actions before execution, but many remain reactive: they primarily assess the apparent safety of the current action, lacking an explicit model of how risk evolves across the trajectory. This limitation creates a critical blind spot for long-horizon risks, where individually benign-looking actions can gradually drift the agent toward hazardous states. In response, we propose DreamGuard, a proactive guardrail for LLM agents built around a risk-aware world model. The world model maintains a compact recurrent latent state over the trajectory and predicts future latent states from which DreamGuard derives immediate-hazard and prefix-risk evidence. It then fuses these multi-horizon signals into intervention decisions before execution. Experiments across four benchmarks and an online guardrail evaluation show that DreamGuard outperforms generic, reactive, and proactive guardrail baselines, achieves the best safety-utility trade-off among evaluated guardrails, and maintains an average end-to-end latency of 25 ms per call.

Stochastic and Private Nonconvex Outlier-Robust PCA

We develop theoretically guaranteed stochastic methods for outlier-robust PCA. Outlier-robust PCA seeks an underlying low-dimensional linear subspace from a dataset that is corrupted with outliers. We are able to show that our methods, which involve stochastic geodesic gradient descent over the Grassmannian manifold, converge and recover an underlying subspace in various regimes through the development of a novel convergence analysis. The main application of this method is an effective differentially private algorithm for outlier-robust PCA that uses a Gaussian noise mechanism within the stochastic gradient method. Our results emphasize the advantages of the nonconvex methods over another convex approach to solving this problem in the differentially private setting. Experiments on synthetic and stylized data verify these results.