When Does Muon Help Agentic Reinforcement Learning?

תקציר מקורי באנגליתarXiv:2607.16169v3 Announce Type: replace Abstract: Muon is competitive with AdamW in large-scale pre-training, but its operating regime in reinforcement-learning post-training remains unclear. We map this regime on ALFWorld, a sparse-reward agentic benchmark, using three group-based objectives and Qwen2.5 models from 0.5B to 3B. Under a shared KL and clipping recipe, matched optimizer comparisons and AdamW learning-rate controls trace the usable step-size range. AdamW responds non-monotonically to its learning rate, whereas fan-in Muon remains stable at a more aggressive effective step. At a learning rate of 3 x 10^-5, it improves late success over an AdamW 10^-6 baseline after correction across rate-metric tests. Its normalized-AUC effect is directionally positive but less uniform; the h