mlsanityData to 14 Oct 2026

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

arXiv 2508.01604 ↗First posted 3 Aug 2025cs.LGcited by 3

On the map: LLM reasoning → Reinforcement learning for reasoning

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.

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.

Builds on

17 of 54 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025MiMo: Unlocking the Reasoning Potential of Language Model -- From Pretraining to Posttraining12 May
  2. 2025FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient Training R1-like Reasoning Models21 Mar
  3. 2025Process Reinforcement through Implicit Rewards3 Feb
  4. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning22 Jan
  5. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMs22 Jan
  6. 2024Free Process Rewards without Process Labels2 Dec

Other references · 11

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2024Qwen2.5 Technical Reportcited by 4,942
  4. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  5. 2024OpenAI o1 System Cardcited by 1,244
  6. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  7. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 487
  8. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 313
  9. 2024Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Modelscited by 284
  10. 2025Phi-4-reasoning Technical Reportcited by 151
  11. 2024Back to Basics: Revisiting REINFORCE Style Optimization for Learning from Human Feedback in LLMscited by 108

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025Verifying Meta-Awareness via Predictive Rewards in Reasoning Modelscited by 3
  2. 2026Temporally Extended Mixture-of-Experts Modelscited by 3
  3. 2025V-Math: An Agentic Approach to the Vietnamese National High School Graduation Mathematics Examscited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2025Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
  2. 2025Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
  3. 2025How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study
  4. 2025Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts
  5. 2025Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning
  6. 2025LogicPuzzleRL: Cultivating Robust Mathematical Reasoning in LLMs via Reinforcement Learning
  7. 2025QuestA: Expanding Reasoning Capacity in LLMs via Question Augmentation
  8. 2025Does Math Reasoning Improve General LLM Capabilities? Understanding Transferability of LLM Reasoning