English

ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning

Machine Learning 2025-09-26 v1 Artificial Intelligence Computation and Language

Abstract

Large Reasoning Models (LRMs) have shown impressive capabilities in complex problem-solving, often benefiting from training on difficult mathematical problems that stimulate intricate reasoning. Recent efforts have explored automated synthesis of mathematical problems by prompting proprietary models or large-scale open-source models from seed data or inherent mathematical concepts. However, scaling up these methods remains challenging due to their high computational/API cost, complexity of prompting, and limited difficulty level of the generated problems. To overcome these limitations, we propose ScaleDiff, a simple yet effective pipeline designed to scale the creation of difficult problems. We efficiently identify difficult problems from existing datasets with only a single forward pass using an adaptive thinking model, which can perceive problem difficulty and automatically switch between "Thinking" and "NoThinking" modes. We then train a specialized difficult problem generator (DiffGen-8B) on this filtered difficult data, which can produce new difficult problems in large scale, eliminating the need for complex, per-instance prompting and its associated high API costs. Fine-tuning Qwen2.5-Math-7B-Instruct on the ScaleDiff-Math dataset yields a substantial performance increase of 11.3% compared to the original dataset and achieves a 65.9% average accuracy on AIME'24, AIME'25, HMMT-Feb'25, BRUMO'25, and MATH500, outperforming recent strong LRMs like OpenThinker3. Notably, this performance is achieved using the cost-efficient Qwen3-8B model as a teacher, demonstrating that our pipeline can effectively transfer advanced reasoning capabilities without relying on larger, more expensive teacher models. Furthermore, we observe a clear scaling phenomenon in model performance on difficult benchmarks as the quantity of difficult problems increases. Code: https://github.com/QizhiPei/ScaleDiff.

Keywords

Cite

@article{arxiv.2509.21070,
  title  = {ScaleDiff: Scaling Difficult Problems for Advanced Mathematical Reasoning},
  author = {Qizhi Pei and Zhuoshi Pan and Honglin Lin and Xin Gao and Yu Li and Zinan Tang and Conghui He and Rui Yan and Lijun Wu},
  journal= {arXiv preprint arXiv:2509.21070},
  year   = {2025}
}

Comments

15 pages

R2 v1 2026-07-01T05:55:58.738Z