Squeeze the Soaked Sponge: Efficient Off-policy RFT for Large Language Model

Jing Liang, Jinyi Liu, Yi Ma, Hongyao Tang, YAN ZHENG, Shuyue Hu, LEI BAI, Jianye HAO

Keywords: Reinforcement Finetuning, Large Language Model, Reasoning

Abstract: Reinforcement Learning (RL) has demonstrated its potential to improve the reasoning ability of Large Language Models (LLMs), yet most existing Reinforcement Finetuning (RFT) methods are inherently *on-policy* RL, failing to reuse historical data and thus preventing efficient scaling. In this work, we explore the potential of *off-policy* RL to leverage historical data for rollout-efficient RFT. Specifically, we propose **Re**incarnating **Mix**-policy Proximal Policy Gradient (**ReMix**), which enables on-policy RFT methods to leverage off-policy data. ReMix consists of three major components: (1) Mix-policy proximal policy gradient with an increased Update-To-Data (UTD) ratio that utilizes the data from both current and past policies for efficient training; (2) KL-Convex policy constraint that combines the KL constraints on the base and precedent model to balance stability and flexibility; (3) Policy reincarnation that replaces the base model with the mix-policy RFT model in the mid way of training and restarts on-policy training, to achieve a seamless transition from early efficiency to steady convergence. In our experiments, we train a series of ReMix models based on PPO, GRPO from 1.5B, 7B base models. On five math reasoning benchmarks (i.e., AIME'24, AMC'23, Minerva, OlympiadBench, and MATH500), ReMix achieves an average Pass@1 accuracy of **52.10%** (with **0.079M rollouts**) and **64.39%** (with **0.011M rollouts**) on 1.5B and 7B models, respectively. Compared with 15 recent advanced models, ReMix shows SOTA-level performance with an over **30x to 450x reduction in training cost in terms of rollout data volume**, demonstrating superior training efficiency. Additionally, our multifaceted analysis reveals insightful findings, including the implicit preference for shorter responses of off-policy RFT, the collapse mode of self-reflection under severe off-policyness, etc. The code and the trained models are available at https://anitaleungxx.github.io/ReMix/ .

Primary Area: foundation or frontier models, including LLMs

Submission Number: 2260