🚀 GRPO-LEAD: Efficient Reasoning Enhancement for Mathematical Tasks

📚 Overview

GRPO-LEAD (GRPO with Length-dependent rewards, Explicit penalties, and Advantage reweighting for Difficulty) is an advanced reinforcement learning pipeline designed to fine-tune large language models (LLMs) for concise, accurate, and efficient reasoning in mathematical tasks.

📊 Performance Benchmarks

The following benchmarks were conducted on AIME24 and AIME25 datasets, evaluated with parameters: 14k maximum tokens, temperature of 0.6, min-p of 0.01, and 32 samples per question.

Model	AIME24 Cons@32	AIME24 Pass@1	AIME24 Avg. Length	AIME25 Cons@32	AIME25 Pass@1	AIME25 Avg. Length
DeepSeek-Distlled-14B	0.800	0.614	9182	0.633	0.429	10046
Light-R1-14B-DS	0.833	0.641	9571	0.767	0.505	10194
LEAD-14B (ours)	0.867	0.650	8267	0.767	0.539	8668

Our GRPO-LEAD model achieves superior consistency and higher accuracy, demonstrating significantly improved reasoning efficiency as evidenced by shorter average reasoning lengths.

⚙️ Usage

To achieve the best performance in solving mathematical problems, simply use the following prompt format:

[
    {
        "role": "user",
        "content": question + "\nLet's think step by step and output the final answer within \\boxed{}."
    }
]

📂 Code and Documentation

For complete details, codebase, and usage examples, please visit our GitHub repository:

📌 GitHub Repository

📦 Dataset: GRPO-LEAD-SFTData

We release GRPO-LEAD-SFTData, a curated collection of 12,153 high-quality mathematical reasoning samples for supervised fine-tuning. Generated via QwQ-32B. Derived primarily from the DeepScaler dataset (DeepScaler), we retain only examples with difficulty > 1, targeting challenging problem-solving scenarios. All entries are structured for seamless integration with LLaMA Factory and follow a standardized SFT-ready format.

Used as the training data for GRPO-LEAD’s supervised fine-tuning stage, this dataset is able to increase the model's base capability in solving mathematical problems.,

📖 Citation

If you find our work useful, please cite it as:

@misc{zhang2025grpoleaddifficultyawarereinforcementlearning,
      title={GRPO-LEAD: A Difficulty-Aware Reinforcement Learning Approach for Concise Mathematical Reasoning in Language Models}, 
      author={Jixiao Zhang and Chunsheng Zuo},
      year={2025},
      eprint={2504.09696},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2504.09696}, 
}

Enjoy exploring GRPO-LEAD! 🚀✨

PlanePaper
/

LEAD-14B