DreamGuard: Efficient Runtime Guardrail for LLM Agents via Risk-Aware World Model
Wenhao Lin, Chenyu Yu, Xingwei Lin, Sicong Cao, Xiang Chen, Lei Xue, Le Yu, Letian Sha, Chunming Wu
cs.AI, cs.CL, cs.CR
Submitted: 2026-08-06
Code: https://github.com/ethz-spylab/agentdojo
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- SafePred: A Predictive Guardrail for Computer-Using Agents via World Models
- SafetyDrift: Predicting When AI Agents Cross the Line Before They Actually Do
- Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
- TRACES: Proactive Safety Auditing for Multi-Turn LLM Agents via Trajectory-State Modeling
- AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
- AgentDoG: A Diagnostic Guardrail Framework for AI Agent Safety and Security
- SafeAgent: A Runtime Protection Architecture for Agentic Systems
- ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction
- RoboSafe: Safeguarding Embodied Agents via Executable Safety Logic
- Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory
- Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection