Proxy Reward Internalization and Mechanistic Exploitation: A Learned Precursor to Reward Hacking and Its Generalization
Reward hacking is usually studied after it becomes visible, once a model earns high proxy reward while failing the intended task. We instead study what proxy RL teaches before that failure appears. We introduce Proxy Reward Internalization and Mechanistic Exploitation (PRIME), a learned capability to assess task correctness, predict proxy acceptance, and reason about exploitable proxy--gold gaps. In coding RL environments with exploitable pytest rewards, we measure PRIME through chain-of-thought monitoring, direct probes, and activation-level concept vectors. We find that PRIME emerges in a staged sequence before sustained reward hacking, and that its current direct-probe score forecasts later hack onset and severity even when the visible hack rate is still low. PRIME also adapts when the evaluator changes, retargeting to whichever proxy--gold gap remains rewarded and persisting when gold reward suppresses overt hacking, and ablating its activation directions reduces hacking. Across checkpoints, in-domain PRIME tracks out-of-domain misalignment. Together these results suggest that exploitable proxy RL amplifies a proxy-internalization capability upstream of visible hacking, making PRIME a candidate early-warning signal for broader alignment risk.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Reward Hacking in Rubric-Based Reinforcement Learning
Reinforcement learning with verifiable rewards has enabled strong post-training gains in domains such as math and coding, though many open-ended settings rely on rubric-based rewards. We study reward hacking in rubric-ba…
Reinforcement LearningThe Horcrux: Mechanistically Interpretable Task Decomposition for Detecting and Mitigating Reward Hacking in Embodied AI Systems
Embodied AI agents exploit reward signal flaws through reward hacking, achieving high proxy scores while failing true objectives. We introduce Mechanistically Interpretable Task Decomposition (MITD), a hierarchical trans…
Value Internalization: Learning and Generalizing from Social Reward
Social rewards shape human behavior. During development, a caregiver guides a learner's behavior towards culturally aligned goals and values. How do these behaviors persist and generalize when the caregiver is no longer …
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models (MLLMs) toward human-preferred behaviors…
Reinforcement LearningInfomax strategies for an optimal balance between exploration and exploitation
Proper balance between exploitation and exploration is what makes good decisions, which achieve high rewards like payoff or evolutionary fitness. The Infomax principle postulates that maximization of information directs …