Alibaba· QwenResearch paper

SAPO: A Stable and Performant Reinforcement Learning Method for Training Large Language Models

A new reinforcement learning method called SAPO (Soft Adaptive Policy Optimization) is introduced for training large language models, replacing hard clipping with a smooth, temperature-controlled gating function to improve stability and performance.

From the source

To address these limitations, we propose Soft Adaptive Policy Optimization (SAPO), an RL method designed for stable and performant optimization of LLMs.

qwen.ai

Announced

04 Dec 2025 20:00 UTC

Detected

28 Aug 2026 13:23 UTC (+266d after)