Training large reasoning models only on safety verification tasks internalizes safety understanding and boosts robustness to out-of-domain jailbreaks, providing a stronger base for reinforcement learning alignment than standard supervised fine-tuning.
Risky- bench: Probing agentic safety risks under real-world de- ployment.CoRR, abs/2602.03100
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
dataset 1
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3representative citing papers
The paper systematizes security for LLM agents in agentic commerce into five threat dimensions, identifies 12 cross-layer attack vectors, and proposes a layered defense architecture.
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.
citing papers explorer
-
Internalizing Safety Understanding in Large Reasoning Models via Verification
Training large reasoning models only on safety verification tasks internalizes safety understanding and boosts robustness to out-of-domain jailbreaks, providing a stronger base for reinforcement learning alignment than standard supervised fine-tuning.
-
SoK: Security of Autonomous LLM Agents in Agentic Commerce
The paper systematizes security for LLM agents in agentic commerce into five threat dimensions, identifies 12 cross-layer attack vectors, and proposes a layered defense architecture.
-
Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability
The paper develops a unified framework that organizes computer-use agent reliability around perception-decision-execution layers and creation-deployment-operation-maintenance stages to map security and alignment interventions.