Calibrated Clipping is proposed, a dynamic method that aligns the FP8 clipping bounds with high-precision BF16 distributions by matching the lower-bound clipping quantile and rebalancing the upper bound accordingly, which eliminates entropy surges and restores performance comparable to the BF16 baseline.
Abstract
Reinforcement learning (RL) has become a key technique for improving the reasoning and agentic abilities of large language models (LLMs). Although FP8 quantization can accelerate RL training, maintaining stability throughout an FP8 RL pipeline remains challenging. While previous works have focused on resolving train-inference mismatches using correction techniques like TIS, we reveal that full-pipeline FP8 RL still suffers from severe training instability, manifesting as anomalous mid-training entropy surges and garbled outputs. We trace this instability to a previously overlooked cause: compounded FP8 quantization noise distorts the importance ratio, disproportionately pushing negative-advantage tokens outside the trust region and erroneously zeroing out their gradients. As a result, pathological outputs are not properly penalized and accumulate over the course of training. To address this, we propose Calibrated Clipping, a dynamic method that aligns the FP8 clipping bounds with high-precision BF16 distributions by matching the lower-bound clipping quantile and rebalancing the upper bound accordingly. Extensive experiments across GRPO and DAPO algorithms, model scales from 8B to 32B, and multiple FP8 scaling granularities demonstrate that our approach successfully eliminates entropy surges and restores performance comparable to the BF16 baseline.
Reinforcement learning has greatly advanced the capabilities of large language models, but its memory demands remain a barrier to broader adoption. We introduce LoGRA, an approach to RL post-training that reduces memory by retaining useful learning signals in low-rank gradient sketches. These compact representations su...
Shao-Kun Zhang, Yi-Fan Zhang, Jian Hu et al.· 1 citation· ⚡1
This work empirically study the potential of outer prefixes, revealing the mechanism of the impact of distributional discrepancy to the exploration dynamics in RLVR training and efficiently mitigates entropy collapse without requiring additional SFT, intricate reward designs, or complex prompting.
Xin Shen, Huishuai Zhang, Peng Li et al.· 2 citations· ⚡1
ACPO is a practical and effective alternative to conventional IS-ratio clipping for RL post-training of LLMs, and establishes a connection between ACPO and gradient clipping in policy mirror descent (PMD), which is a standard technique to stabilize optimization process.
It is shown that the instability of RL under TIM is primarily caused by drift: a persistent bias between training and inference engines that accumulates with every training step, and an additive score centering term is derived that stabilizes RL under TIM by canceling drift.
Martina Marek, Max Ryabinin· arXiv.org· 11 citations· ⚡3
This paper characterize the interaction between mismatch and the policy-gradient direction, distinguishing locally amplifying from contracting update contributions that mismatch magnitude alone cannot identify and introduces TRIAGE, a direction-aware stabilization method that uses segment-level diagnosis to selectively...
Zhen Li, Shuai Zhang, Yang-Gan Gu et al.· 1 citation
Large language models (LLMs) are typically pretrained in high precision but increasingly deployed with low-precision post-training quantization (PTQ). Recent studies have shown that using weight averaging during pretraining can improve PTQ performance compared with learning-rate decay, suggesting that it might provide...
Han Wang, Tianqi Shen, Zong-Lin Liu et al.· 0 citations
Related blog posts
MIT News · Artificial Intelligence· news.mit.eduOct 13, 2026
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
MIT News · Artificial Intelligence· news.mit.eduSep 29, 2026
Professor Sherry Turkle’s new book, “Artificial Intimacy,” offers a withering critique of chatbots and the antisocial dynamics she believes they encourage.