AI Paper Atlas

Research map / Reinforcement learning / RL from feedback

QeRL: Beyond Efficiency - Quantization-enhanced Reinforcement Learning for LLMs

Wei Huang, Yi Ge, Shuai Yang, Yicheng Xiao, Huizi Mao, Yujun Lin, Hanrong Ye, Sifei Liu, Ka Chun Cheung, Hongxu Yin, Yao Lu, Xiaojuan Qi and 2 more

ICLR 2026 · Reinforcement learning › RL from feedback · approach: RL for LLM reasoning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add Adaptive Quantization Noise on top of NVFP4 + LoRA (ablation)QeRL · GSM8K, GRPOaccuracy: 88.5 -> 90.8 (7B); 83.3 -> 83.7 (3B)Improved
add AQN on top of NVFP4 + LoRA (ablation)QeRL · BigMath DAPO, average of 4 benchmarksaverage accuracy: 7B: 37.0 -> 36.4; 14B: 40.5 -> 42.0; 32B: 41.4 -> 45.6Mixed
quantize policy weights to NVFP4 with LoRA instead of BF16 LoRA (ablation)RL with LoRA · GSM8K, GRPOaccuracy: 88.1 -> 88.5 (7B); 76.1 -> 83.3 (3B)Improved
use NVFP4 instead of NF4 quantization for RL with LoRA (ablation)QLoRA · GSM8K, GRPOaccuracy: 85.0 -> 88.5 (7B)Improved
use NVFP4 instead of MXFP4 (ablation)QeRL · GSM8K, GRPOaccuracy: 86.4 -> 88.5 (7B); 73.4 -> 83.3 (3B)Improved
replace NF4 QLoRA with NVFP4 QeRL for speedRL training · end-to-end GRPO trainingspeedup vs LoRA: x0.8 -> x1.5 (7B, batch 2)Improved
exponential decay noise schedule instead of linear, cosine or logarithmic (ablation)AQN · GSM8K, Qwen2.5-3BrewardImproved
vary LoRA rank among 16, 32, 64, 128 (ablation)QeRL · GSM8K, Qwen2.5-3Breward growthNo clear effect
raise learning rate to 3e-5 (ablation)QeRL vs BF16 LoRA · Qwen2.5-7B-Instructtraining stabilityMixed
compare quantized model with no RL trainingNVFP4 post-training quantization · MATH500 etc., 7Baverage accuracy: 28.9 -> 25.7Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy