# Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention

arXiv: https://arxiv.org/abs/2508.01604 · HTML: https://mlsanity.com/paper/2508.01604/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 17 of its 54 references that are in the map.
- First posted on arXiv 3 Aug 2025.

## Placed in

- LLM reasoning / [Reinforcement learning for reasoning](https://mlsanity.com/lr/reinforcement-learning-for-reasoning/)

## Builds on (most cited first, 17 of 17)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [OpenAI o1 System Card](https://mlsanity.com/paper/2412.16720/) (2024)
- [Kimi k1.5: Scaling Reinforcement Learning with LLMs](https://mlsanity.com/paper/2501.12599/) (2025)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [Process Reinforcement through Implicit Rewards](https://mlsanity.com/paper/2502.01456/) (2025)
- [MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning](https://mlsanity.com/paper/2309.05653/) (2023)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024)
- [Free Process Rewards without Process Labels](https://mlsanity.com/paper/2412.01981/) (2024)
- [Phi-4-reasoning Technical Report](https://mlsanity.com/paper/2504.21318/) (2025)
- [MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining](https://mlsanity.com/paper/2505.07608/) (2025)
- [Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMs](https://mlsanity.com/paper/2402.14740/) (2024)
- [FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient Training R1-like Reasoning Models](https://mlsanity.com/paper/2503.17287/) (2025)

## Built on by (most cited first, 3 of 3)

- [Verifying Meta-Awareness via Predictive Rewards in Reasoning Models](https://mlsanity.com/paper/2510.03259/) (2025)
- [Temporally Extended Mixture-of-Experts Models](https://mlsanity.com/paper/2604.20156/) (2026)
- [V-Math: An Agentic Approach to the Vietnamese National High School Graduation Mathematics Exams](https://mlsanity.com/paper/2509.12251/) (2025)

## Abstract (arXiv)

Reinforcement learning scaling enhances the reasoning capabilities of large language models, with reinforcement learning serving as the key technique to draw out complex reasoning. However, key technical details of state-of-the-art reasoning LLMs, such as those in the OpenAI O series, Claude 3 series, DeepMind's Gemini 2.5 series, and Grok 3 series, remain undisclosed, making it difficult for the research community to replicate their reinforcement learning training results. Therefore, we start our study from an Early Preview Reinforcement Learning (EPRLI) algorithm built on the open-source GRPO framework, incorporating difficulty-aware intervention for math problems. Applied to a 1.5B-parameter LLM, our method achieves 50.0% on AIME24, 89.2% on Math500, 77.1% on AMC, 35.3% on Minerva, and 51.9% on OBench, superpass O1-Preview and is comparable to O1-mini within standard school-lab settings.