Shortcut Sensitivity in Agent-Safety Evaluations

cs.AI, cs.CR, cs.LG

Submitted: 2026-10-15

Updated: 2026-10-15

Comments: Accepted at the NeurIPS 2026 workshops TAE (Can We Trust AI Evaluation?) and AIWILD (Agents in the Wild: Safety, Security, and Beyond)

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

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