A lightweight learned model of an agent's trajectory can flag both immediate hazards and slowly accumulating risks before actions execute, improving safety while preserving task utility.
Proceedings of the 43rd International Conference on Machine Learning (ICML) , year =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model
A lightweight learned model of an agent's trajectory can flag both immediate hazards and slowly accumulating risks before actions execute, improving safety while preserving task utility.