SOURCE-LINKED INTELLIGENCE

Expert-Space Exploration in MoE Reinforcement Learning

arXiv · AI, language, vision and robotics · article · Sep 11, 2026 · UTC

Reinforcement learning (RL) has become central to post-training of large language models. Recent advances in RL for Mixture-of-Experts (MoE) models have primarily focused on improving optimization stability and training efficiency, while treating the expert selection as a fixed component. Since routing determines the sparse computation paths that induce output distributions, expert selection offers an additional source of rollout diversity. Through empirical analysis, we find that perturbing expert routing effectively alters model output and increases rollout diversity, which is similar to inc

Read original source ↗ Open in workspace

recordType

paper

region

Global