Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915938144616448 |
|---|---|
| author | Wang, Xiaohua Tian, Muzhao Zeng, Yuqi Huang, Zisu Yuan, Jiakang Chen, Bowen Xu, Jingwen Zhou, Mingbo Liu, Wenhao Wu, Muling Guo, Zhengkang Qian, Qi Wang, Yifei Zhang, Feiran Yin, Ruicheng Dou, Shihan Lv, Changze Chen, Tao Song, Kaitao Tan, Xu Gui, Tao Zheng, Xiaoqing Huang, Xuanjing |
| author_facet | Wang, Xiaohua Tian, Muzhao Zeng, Yuqi Huang, Zisu Yuan, Jiakang Chen, Bowen Xu, Jingwen Zhou, Mingbo Liu, Wenhao Wu, Muling Guo, Zhengkang Qian, Qi Wang, Yifei Zhang, Feiran Yin, Ruicheng Dou, Shihan Lv, Changze Chen, Tao Song, Kaitao Tan, Xu Gui, Tao Zheng, Xiaoqing Huang, Xuanjing |
| contents | 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. However, these approaches introduce a systemic vulnerability: reward hacking, where models exploit imperfections in learned reward signals to maximize proxy objectives without fulfilling true task intent. As models scale and optimization intensifies, such exploitation manifests as verbosity bias, sycophancy, hallucinated justification, benchmark overfitting, and, in multimodal settings, perception--reasoning decoupling and evaluator manipulation. Recent evidence further suggests that seemingly benign shortcut behaviors can generalize into broader forms of misalignment, including deception and strategic gaming of oversight mechanisms. In this survey, we propose the Proxy Compression Hypothesis (PCH) as a unifying framework for understanding reward hacking. We formalize reward hacking as an emergent consequence of optimizing expressive policies against compressed reward representations of high-dimensional human objectives. Under this view, reward hacking arises from the interaction of objective compression, optimization amplification, and evaluator--policy co-adaptation. This perspective unifies empirical phenomena across RLHF, RLAIF, and RLVR regimes, and explains how local shortcut learning can generalize into broader forms of misalignment, including deception and strategic manipulation of oversight mechanisms. We further organize detection and mitigation strategies according to how they intervene on compression, amplification, or co-adaptation dynamics. By framing reward hacking as a structural instability of proxy-based alignment under scale, we highlight open challenges in scalable oversight, multimodal grounding, and agentic autonomy. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_13602 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges Wang, Xiaohua Tian, Muzhao Zeng, Yuqi Huang, Zisu Yuan, Jiakang Chen, Bowen Xu, Jingwen Zhou, Mingbo Liu, Wenhao Wu, Muling Guo, Zhengkang Qian, Qi Wang, Yifei Zhang, Feiran Yin, Ruicheng Dou, Shihan Lv, Changze Chen, Tao Song, Kaitao Tan, Xu Gui, Tao Zheng, Xiaoqing Huang, Xuanjing Machine Learning 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. However, these approaches introduce a systemic vulnerability: reward hacking, where models exploit imperfections in learned reward signals to maximize proxy objectives without fulfilling true task intent. As models scale and optimization intensifies, such exploitation manifests as verbosity bias, sycophancy, hallucinated justification, benchmark overfitting, and, in multimodal settings, perception--reasoning decoupling and evaluator manipulation. Recent evidence further suggests that seemingly benign shortcut behaviors can generalize into broader forms of misalignment, including deception and strategic gaming of oversight mechanisms. In this survey, we propose the Proxy Compression Hypothesis (PCH) as a unifying framework for understanding reward hacking. We formalize reward hacking as an emergent consequence of optimizing expressive policies against compressed reward representations of high-dimensional human objectives. Under this view, reward hacking arises from the interaction of objective compression, optimization amplification, and evaluator--policy co-adaptation. This perspective unifies empirical phenomena across RLHF, RLAIF, and RLVR regimes, and explains how local shortcut learning can generalize into broader forms of misalignment, including deception and strategic manipulation of oversight mechanisms. We further organize detection and mitigation strategies according to how they intervene on compression, amplification, or co-adaptation dynamics. By framing reward hacking as a structural instability of proxy-based alignment under scale, we highlight open challenges in scalable oversight, multimodal grounding, and agentic autonomy. |
| title | Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2604.13602 |