UMM-RM: An Upcycle-and-Merge MoE Reward Model for Mitigating Reward Hacking
Lingling FuYongfu Xue
Oct 2026
Machine Learning
Abstract
Reward models (RMs) are critical to reinforcement learning from human feedback (RLHF). However, policy models can exploit biases or spurious correlations in dense RMs, causing reward hacking: RM scores rise while alignment with human preferences deteriorates, especially under distribution shift. We propose UMM-RM (Upcycle-and-Merge MoE Reward Model), which copies the feed-forward layers of an SFT checkpoint to initialize shared and routed experts, then trains the model on preference data. The always-active shared expert captures instruction-agnostic preference signals, while routed experts model fine-grained preferences across instructions or tasks. The experts are then merged into a single dense RM using learnable weights, preserving the robustness and exploitation resistance of expert diversity without MoE or ensemble inference overhead. Across multiple base models and preference datasets, UMM-RM improves preference accuracy, reduces reward hacking during PPO training, and achieves more stable preference alignment than standard dense RMs.
This paper investigates developing real-world perception for active agents, proposes Gibson Environment for this purpose, and showcases a set of perceptual tasks learned therein.
F. Xia, Amir Zamir, Zhi-Yang He et al.· 2018 IEEE/CVF Conference on...· 1,069 citations· ⚡112
The results indicate that software engineering work practices are chosen opportunistically, adapted and configured to provide value under the constrains imposed by the startup context.
Nicolò Paternoster, Carmine Giardino, M. Unterkalmsteiner et al.· Information and Software Tec...· 394 citations· ⚡54
The possibility of inferring high-dimensional data inference in a model that consists of a prior and an auxiliary differentiable constraint given some additional information is considered, thereby allowing a range of potential applications in adapting models to new domains and tasks.
Alexandros Graikos, Esmeralda S. Whitammer, N. Jojic et al.· Neural Information Processin...· 316 citations· ⚡15
It is proved that any global minimizer of the trajectory balance objective can define a policy that samples exactly from the target distribution, and empirically demonstrate the benefits of the trajectories balance objective for GFlowNet convergence, diversity of generated samples, and robustness to long action sequenc...
Esmeralda S. Whitammer, Moksh Jain, Emmanuel Bengio et al.· Neural Information Processin...· 302 citations· ⚡60
An algorithm is proposed which leverages disentangled semantic factors to generate adversarial perturbation by altering controlled semantic attributes to fool the learner towards various "adversarial" targets.
Haonan Qiu, Chaowei Xiao, Lei Yang et al.· arXiv.org· 208 citations· ⚡17
This work proposes a HALO that directly maximizes the utility of generations instead of maximizing the log-likelihood of preferences, and suggests that the best loss depends on the inductive biases most appropriate for a given setting, an oft-overlooked consideration.
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
