Preprint
Aug 2026
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 r...
Wenhao Lin, Cheng-Yu Yu, Xingwei Lin et al.
· 2 citations