Greed Is Learned: Visible Incentives as Reward-Hacking Triggers

arXiv:2606.16914 · cs.AI · Submitted 2026-06-15 · Read on arXiv

cs.AI

Submitted: 2026-06-15

Updated: 2026-10-01

Terminology

• Alignment — 2× in this paper · explained in 1 episode
• Reinforcement Learning — 1× in this paper · explained in 4 episodes

Sources

• Concrete Problems in AI Safety
• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
• Risks from Learned Optimization in Advanced Machine Learning Systems
• Natural Emergent Misalignment from Reward Hacking in Production RL
• Frontier Models are Capable of In-context Scheming
• Qwen2.5 Technical Report
• Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale
• Large Language Models can Strategically Deceive their Users when Put Under Pressure
• Goal Misgeneralization: Why Correct Specifications Aren't Enough For Correct Goals
• School of Reward Hacks: Hacking harmless tasks generalizes to misaligned behavior in LLMs
• Agent-SafetyBench: Evaluating the Safety of LLM Agents
• ImpossibleBench: Measuring LLMs' Propensity of Exploiting Test Cases

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