Wang, X., Yu, H., Zhuge, Z., Mao, B., Li, Z., Feng, J., Luo, Y., Zhang, Y., Cao, Y., Zhang, M., Liu, D., & Zhang, J. (2026). TRACE: Rollout-Guided Quantization-Aware Training for FP4 Reinforcement Learning of MoE Language Models. https://omanscience.com/ar/articles/trace-rollout-guided-quantization-aware-training-for-fp4-reinforcement-learning-of-moe-language-models