SafeHarbor introduces a hierarchical memory-augmented guardrail with adversarial rule extraction and entropy-driven self-evolution to balance safety and utility in LLM agents.
International Conference on Learning Representations , volume=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
citing papers explorer
-
SafeHarbor: Hierarchical Memory-Augmented Guardrail for LLM Agent Safety
SafeHarbor introduces a hierarchical memory-augmented guardrail with adversarial rule extraction and entropy-driven self-evolution to balance safety and utility in LLM agents.
- Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents