# When Does Muon Help Agentic Reinforcement Learning?

arXiv: https://arxiv.org/abs/2607.16169 · HTML: https://mlsanity.com/paper/2607.16169/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 17 Jul 2026.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 19 of 19)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [WebShop: Towards Scalable Real-World Web Interaction with Grounded Language Agents](https://mlsanity.com/paper/2207.01206/) (2022)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [Muon is Scalable for LLM Training](https://mlsanity.com/paper/2502.16982/) (2025)
- [Muon Optimizes Under Spectral Norm Constraints](https://mlsanity.com/paper/2506.15054/) (2025)
- [Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning](https://mlsanity.com/paper/2605.26684/) (2026)
- [Preconditioning Benefits of Spectral Orthogonalization in Muon](https://mlsanity.com/paper/2601.13474/) (2026)
- [Adam Improves Muon: Adaptive Moment Estimation with Orthogonalized Momentum](https://mlsanity.com/paper/2602.17080/) (2026)
- [HTMuon: Improving Muon via Heavy-Tailed Spectral Correction](https://mlsanity.com/paper/2603.10067/) (2026)
- [Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR](https://mlsanity.com/paper/2605.19282/) (2026)
- [CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning](https://mlsanity.com/paper/2606.29476/) (2026)
- [Can Muon Fine-tune Adam-Pretrained Models?](https://mlsanity.com/paper/2605.10468/) (2026)
- [Optimizer-Model Consistency: Full Finetuning with the Same Optimizer as Pretraining Forgets Less](https://mlsanity.com/paper/2605.06654/) (2026)
- [MiMuon: Mixed Muon Optimizer with Improved Generalization for Large Models](https://mlsanity.com/paper/2605.19619/) (2026)
- [Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents](https://mlsanity.com/paper/2606.25852/) (2026)

## Built on by (most cited first, 1 of 1)

- [Long-Horizon RL Needs Muon](https://mlsanity.com/paper/2610.20256/) (2026)

## Abstract (arXiv)

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 rate controls trace the usable step-size range. AdamW responds non-monotonically to rate, whereas fan-in Muon remains stable at a more aggressive effective step: at 3 × 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 heuristic-matched lower-rate effect is less consistent, and tuned AdamW nearly matches high-rate Muon at 3B GraphGPO. High-rate Muon applies 3.53 × AdamW's hidden-matrix update RMS; a full-budget RMS-matched control removes the late-success gain. Together, these results identify a recipe-level operating regime in which fan-in Muon supports a more aggressive stable effective step under shared KL and clipping: the margin is largest when optimization headroom remains and contracts near saturation, after AdamW tuning, or under magnitude matching. The scale-matched control ties this spectral effect to Muon's scale convention rather than establishing a universal optimizer ranking. Code is available at https://github.com/x66ccff/verl-muon.