ProbGuard: Proactive Runtime Monitoring for LLM Agent Safety via Probabilistic Prediction

arXiv:2508.00500 · cs.AI, cs.SE · Submitted 2025-08-01 · Read on arXiv

cs.AI, cs.SE

Submitted: 2025-08-01

Updated: 2026-08-03

Terminology

• Abstraction — 1× in this paper · explained in 1 episode
• Large Language Model — 1× in this paper
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Sample Complexity — 1× in this paper · explained in 17 episodes
• Trace — 1× in this paper · explained in 2 episodes

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
• Agents' Last Exam
• 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