CheatBench: Measuring Reward Gaming in AI Agents

arXiv:2609.36308 · cs.AI · Submitted 2026-09-28 · Read on arXiv

cs.AI

Submitted: 2026-09-28

Updated: 2026-09-28

Terminology

• AI Agents — 1× in this paper · explained in 2 episodes

Sources

• Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values
• EvilGenie: A Reward Hacking Benchmark
• Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
• Agents' Last Exam

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