Elliott/LUFFY-Qwen-Math-7B-Zero-On-Policy

Our on-policy strong baseline. Trained with our OpenR1-Math-220k subset(https://huggingface.co/datasets/Elliott/Openr1-Math-46k-8192).

📖Introduction

LUFFY is a reinforcement learning framework that bridges the gap between zero-RL and imitation learning by incorporating off-policy reasoning traces into the training process. Built upon GRPO, LUFFY combines on-policy rollouts with off-policy demonstrations during advantage estimation and introduces policy shaping via regularized importance sampling to emphasize low-probability yet crucial actions.

Key Highlights:

• —Off-Policy Guidance: Seamlessly integrates external reasoning traces to bootstrap learning from stronger models.
• —Dynamic Balance: Learns when to imitate and when to explore, adapting over the course of training.
• —Policy Shaping: Emphasizes important actions often ignored in standard policy gradients, enabling better generalization.

Inference

Here’s an example of using LUFFY for inference:

from transformers import AutoTokenizer
from vllm import LLM, SamplingParams

model_path="Elliott/LUFFY-Qwen-Math-7B-Zero"

question = "which number is larger? 9.11 or 9.9?"

tokenizer = AutoTokenizer.from_pretrained(model_path)
messages = [{"role": "user", "content": question}]
chat = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)

llm = LLM(model=model_path)
params = SamplingParams(temperature=0.6, max_tokens=8192)
outputs = llm.generate([chat], params)
print(outputs[0].outputs[0].text)

📃Evaluation

LUFFY is evaluated on six competition-level benchmarks, achieving state-of-the-art results among all zero-RL methods. It surpasses both on-policy RL and imitation learning (SFT), especially in generalization:

🌻Acknowledgement

LUFFY builds upon veRL and deepscaler, and utilizes vLLM for inference. We utilize Math-Verify for math reasoning evaluation. We thank the open-source community for datasets and backbones, including NuminaMath, OpenR1-Math-220k, Qwen2.5-Math, and DeepSeek-R1 model.

Code: https://github.com/ElliottYan/LUFFY

Citation

If you find our model, data, or evaluation code useful, please kindly cite our paper:

@misc{luffy,
      title={Learning to Reason under Off-Policy Guidance}, 
      author={Jianhao Yan and Yafu Li and Zican Hu and Zhi Wang and Ganqu Cui and Xiaoye Qu and Yu Cheng and Yue Zhang},
      year={2025},
      eprint={2504.14945},
      archivePrefix={arXiv},
      primaryClass={cs.LG},
      url={https://arxiv.org/abs/2504.14945}, 
}