Poster Sat, Apr 25, 2026 • 6:30 AM – 9:00 AM PDT Pavilion 3 P3-#1416

BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping

Zhiheng Xi ⋅ Xin Guo ⋅ Yang Nan ⋅ Enyu Zhou ⋅ Junrui Shen ⋅ Wenxiang Chen ⋅ Jiaqi Liu ⋅ Jixuan Huang ⋅ Xun Deng ⋅ Zhihao Zhang ⋅ Honglin Guo ⋅ Zhikai Lei ⋅ Miao Zheng ⋅ Guoteng Wang ⋅ Peng Sun ⋅ Rui Zheng ⋅ Hang Yan ⋅ Tao Gui ⋅ Qi Zhang ⋅ Xuanjing Huang

Project Page

Abstract

Reinforcement learning (RL) has recently become the core paradigm for aligning and strengthening large language models (LLMs). Yet, applying RL in off-policy settings—where stale data from past policies are used for training—improves sample efficiency, but remains challenging: policy entropy declines sharply, optimization often becomes unstable and may even collapse. Through theoretical and empirical analysis, we identify two key insights: (i) an imbalance in optimization, where negative-advantage samples dominate the policy gradient, suppressing useful behaviors and risking gradient explosions; and (ii) the derived Entropy-Clip Rule, which reveals that the fixed clipping mechanism in PPO-like objectives systematically blocks entropy-increasing updates, thereby driving the policy toward over-exploitation at the expense of exploration. Building on these insights, we propose BAlanced Policy Optimization with Adaptive Clipping (BAPO), a simple yet effective method that dynamically adjusts clipping bounds to adaptively re-balance positive and negative contributions, preserve entropy, and stabilize RL optimization. Across diverse off-policy scenarios—including sample replay and partial rollout—BAPO achieves fast, stable, and data-efficient training. On AIME 2024 and AIME 2025 benchmarks, our 7B BAPO model surpasses open-source counterparts such as SkyWork-OR1-7B, while our 32B BAPO model not only achieves state-of-the-art results among models of the same scale but also outperforms leading proprietary systems like o3-mini and Gemini-2.5-Flash-Thinking.