# MuonRec: Shifting the Optimizer Paradigm Beyond Adam in Scalable Generative Recommendation

arXiv: https://arxiv.org/abs/2603.00416 · HTML: https://mlsanity.com/paper/2603.00416/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 37 references that are in the map.
- First posted on arXiv 28 Feb 2026.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation](https://mlsanity.com/paper/2002.02126/) (2020)
- [Personalized Top-N Sequential Recommendation via Convolutional Sequence Embedding](https://mlsanity.com/paper/1809.07426/) (2018)
- [Muon is Scalable for LLM Training](https://mlsanity.com/paper/2502.16982/) (2025)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignment](https://mlsanity.com/paper/2502.18965/) (2025)
- [NorMuon: Making Muon more efficient and scalable](https://mlsanity.com/paper/2510.05491/) (2025)
- [Practical Efficiency of Muon for Pretraining](https://mlsanity.com/paper/2505.02222/) (2025)
- [ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation](https://mlsanity.com/paper/2308.11131/) (2023)
- [Large Language Models for Generative Recommendation: A Survey and Visionary Discussions](https://mlsanity.com/paper/2309.01157/) (2023)
- [HLLM: Enhancing Sequential Recommendations via Hierarchical Large Language Models for Item and User Modeling](https://mlsanity.com/paper/2409.12740/) (2024)
- [RankMixer: Scaling Up Ranking Models in Industrial Recommenders](https://mlsanity.com/paper/2507.15551/) (2025)
- [ClickPrompt: CTR Models are Strong Prompt Generators for Adapting Language Models to CTR Prediction](https://mlsanity.com/paper/2310.09234/) (2023)
- [Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation](https://mlsanity.com/paper/2408.03533/) (2024)
- [MiniOneRec: An Open-Source Framework for Scaling Generative Recommendation](https://mlsanity.com/paper/2510.24431/) (2025)
- [Systematic Review of Newton-Schulz Iterations with Unified Factorizations : Integration in the Richardson Method and Application to Robust Failure Detection in Electrical Networks](https://mlsanity.com/paper/2208.04068/) (2022)

## Built on by (most cited first, 2 of 2)

- [Muon Learns More Robust and Transferable Features than Adam](https://mlsanity.com/paper/2606.09658/) (2026)
- [Relative Generalization Invariance of LLM Pretraining](https://mlsanity.com/paper/2609.33016/) (2026)

## Abstract (arXiv)

Recommender systems (RecSys) are increasingly emphasizing scaling, leveraging larger architectures and more interaction data to improve personalization. Yet, despite the optimizer's pivotal role in training, modern RecSys pipelines almost universally default to Adam/AdamW, with limited scrutiny of whether these choices are truly optimal for recommendation. In this work, we revisit optimizer design for scalable recommendation and introduce MuonRec, the first framework that brings the recently proposed Muon optimizer to RecSys training. Muon performs orthogonalized momentum updates for 2D weight matrices via Newton-Schulz iteration, promoting diverse update directions and improving optimization efficiency. We develop an open-source training recipe for recommendation models and evaluate it across both traditional sequential recommenders and modern generative recommenders. Extensive experiments demonstrate that MuonRec reduces converged training steps by an average of 32.4% while simultaneously improving final ranking quality. Specifically, MuonRec yields consistent relative gains in NDCG@10, averaging 12.6% across all settings, with particularly pronounced improvements in generative recommendation models. These results consistently outperform strong Adam/AdamW baselines, positioning Muon as a promising new optimizer standard for RecSys training. Our code is available.