arXiv AI June 3, 2026 By Xiaocan Li, Shiliang Wu, Zheng Shen

Decomposing MXFP4 quantization error for LLM reinforcement learning: reducible bias, recoverable deadzone, and an irreducible floor

arXiv:2605. 20402v3 Announce Type: replace-cross Abstract: MXFP4 arithmetic can dramatically accelerate reinforcement learning (RL) post-training of large language models (LLMs), yet the quantization error introduces severe accuracy degradation.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv Machine Learning

Jul 20

QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual Sides

arXiv:2607. 15810v1 Announce Type: new Abstract: Rollout generation is a major bottleneck in Reinforcement Learning (RL) for Mixture-of-Experts (MoE) Large Language Models, motivating low-precision rollout acceleration such as FP8.

By Zhengyang Zhuge, Hao Yu, Xin Wang, Zheng Li, Yizhong Cao, Dayiheng Liu, Jianwei Zhang

llms reinforcement-learning efficiency benchmarks safety

arXiv Machine Learning

Jul 30

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models

arXiv:2607. 26515v1 Announce Type: new Abstract: We present, to our knowledge, the first end-to-end FP4 RL post-training, in which both the rollout and training policies, including their forward and backward passes, operate at 4-bit precision.

By Hei Yi Mak, Shadan Golestan, Hoang Le, Mehran Taghian Jazi, Yunke Peng, Yaoyuan Wang, Yao Wang, Junsong Wang, Tianchi Hu, Fengchen He, Guipeng Hu, Tanzila Rahman, Anandharaju Durai Raju

llms reinforcement-learning efficiency

arXiv AI

Jul 28

ACRL: Adaptive Control of Training-Inference Discrepancy for Stable Reinforcement Learning

arXiv:2607. 24062v1 Announce Type: cross Abstract: Reinforcement Learning (RL) training for Large Language Models (LLMs) often suffers from instability due to the discrepancy between training and inference.

By Wenwu Fan, Qihong Lin, Zhijie Xia, Zhuo Zheng, Sihao Wang, Qiang Chen, Liangsheng Zhu

llms reinforcement-learning efficiency

arXiv AI

Aug 11

Quantization Degradation in Large Language Models: A Signal-Noise Perspective

arXiv:2608. 08188v1 Announce Type: new Abstract: Post-training quantization reduces the deployment cost of large language models, yet how severely a quantized model degrades is not determined by bit-width alone.

By Chenxi Zhou, Pengfei Cao, Jinyu Ye, Bohan Yu, Haida Yu, Jiang Li, Jun Zhao, Kang Liu

llms efficiency

arXiv AI

Jun 9

Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin

arXiv:2606. 09012v1 Announce Type: cross Abstract: Post-training quantization (PTQ) converts a trained full-precision model into low-bit weights without task-level retraining, while quantization-aware training (QAT) incorporates quantization into the training loop.

By Hanyang Li, Jianhao Ma, Ying Cui

llms efficiency safety

arXiv AI

Jul 29

Stable FP4 Training via Transposition-Invariant Block Quantization

arXiv:2607. 24953v1 Announce Type: cross Abstract: Reducing training precision is a key lever for improving the e ciency of large language model (LLM) training, but pushing beyond FP8 to 4-bit oating point (FP4) remains challenging due to instability during optimization.

By Mehdi Rahimifar, Amin Darabi, Mehran Taghian Jazi, Xing Huang, Yao Wang, Zhijun Tu, Yufei Cui, Yunke Peng, Hongliang Li

llms efficiency

Related stories

QUADS: Stabilizing NVFP4 Reinforcement Learning for MoE via QUantization-error Alignment across Dual Sides

HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models

ACRL: Adaptive Control of Training-Inference Discrepancy for Stable Reinforcement Learning

Quantization Degradation in Large Language Models: A Signal-Noise Perspective

Understanding Quantization-Aware Training: Gradients at Quantized Weights Bias to the Low-Loss Basin

Stable FP4 Training via Transposition-Invariant Block Quantization