# FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient Training R1-like Reasoning Models

arXiv: https://arxiv.org/abs/2503.17287 · HTML: https://mlsanity.com/paper/2503.17287/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for reasoning, one of 17 directions in LLM reasoning.
- Builds on 11 of its 23 references that are in the map.
- First posted on arXiv 21 Mar 2025.

## Placed in

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

## Builds on (most cited first, 11 of 11)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Measuring Mathematical Problem Solving With the MATH Dataset](https://mlsanity.com/paper/2103.03874/) (2021)
- [DAPO: An Open-Source LLM Reinforcement Learning System at Scale](https://mlsanity.com/paper/2503.14476/) (2025)
- [Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters](https://mlsanity.com/paper/2408.03314/) (2024)
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems](https://mlsanity.com/paper/2402.14008/) (2024)
- [Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvement](https://mlsanity.com/paper/2409.12122/) (2024)
- [Demystifying Long Chain-of-Thought Reasoning in LLMs](https://mlsanity.com/paper/2502.03373/) (2025)
- [rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinking](https://mlsanity.com/paper/2501.04519/) (2025)
- [Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systems](https://mlsanity.com/paper/2412.09413/) (2024)

## Built on by (most cited first, 27 of 27)

- [JustRL: Scaling a 1.5B LLM with a Simple RL Recipe](https://mlsanity.com/paper/2512.16649/) (2025)
- [RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformation](https://mlsanity.com/paper/2509.15965/) (2025)
- [Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?](https://mlsanity.com/paper/2507.04632/) (2025)
- [Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR](https://mlsanity.com/paper/2507.15778/) (2025)
- [Stable Reinforcement Learning for Efficient Reasoning](https://mlsanity.com/paper/2505.18086/) (2025)
- [CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs](https://mlsanity.com/paper/2510.01037/) (2025)
- [Does Your Reasoning Model Implicitly Know When to Stop Thinking?](https://mlsanity.com/paper/2602.08354/) (2026)
- [Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Models](https://mlsanity.com/paper/2505.15634/) (2025)
- [CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning](https://mlsanity.com/paper/2509.25004/) (2025)
- [Scheduling Your LLM Reinforcement Learning with Reasoning Trees](https://mlsanity.com/paper/2510.24832/) (2025)
- [From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimization](https://mlsanity.com/paper/2507.06573/) (2025)
- [Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5B](https://mlsanity.com/paper/2511.06221/) (2025)
- [Prompt replay: speeding up grpo with on-policy reuse of high-signal prompts](https://mlsanity.com/paper/2603.21177/) (2026)
- [Hunyuan-MT Technical Report](https://mlsanity.com/paper/2509.05209/) (2025)
- [Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learning](https://mlsanity.com/paper/2512.16917/) (2025)
- [RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning](https://mlsanity.com/paper/2602.21628/) (2026)
- [Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Design](https://mlsanity.com/paper/2506.04734/) (2025)
- [Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Intervention](https://mlsanity.com/paper/2508.01604/) (2025)
- [R^3: Replay, Reflection, and Ranking Rewards for LLM Reinforcement Learning](https://mlsanity.com/paper/2601.19620/) (2026)
- [TACLer: Tailored Curriculum Reinforcement Learning for Efficient Reasoning](https://mlsanity.com/paper/2601.21711/) (2026)
- [LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Models](https://mlsanity.com/paper/2607.28077/) (2026)
- [ETR: Outcome-Guided Elastic Trust Regions for Policy Optimization](https://mlsanity.com/paper/2601.03723/) (2026)
- [MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learning](https://mlsanity.com/paper/2601.17006/) (2026)
- [Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoning](https://mlsanity.com/paper/2601.23027/) (2026)
- [Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoning](https://mlsanity.com/paper/2604.02322/) (2026)
- [HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Models](https://mlsanity.com/paper/2607.26515/) (2026)
- [What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signals](https://mlsanity.com/paper/2610.04978/) (2026)

## Abstract (arXiv)

Improving training efficiency continues to be one of the primary challenges in large-scale Reinforcement Learning (RL). In this paper, we investigate how context length and the complexity of training data influence the RL scaling training process of R1-distilled reasoning models, e.g., DeepSeek-R1-Distill-Qwen-1.5B. Our experimental results reveal that: (1) simply controlling the context length and curating the training data based on the input prompt length can effectively improve the training efficiency of RL scaling, achieving better performance with more concise CoT; (2) properly scaling the context length helps mitigate entropy collapse; and (3) carefully choosing the context length facilitates achieving efficient LLM training and reasoning. Inspired by these insights, we propose FastCuRL, a curriculum RL framework with stage-wise context scaling to achieve efficient LLM training and reasoning. Extensive experimental results demonstrate that FastCuRL-1.5B-V3 significantly outperforms state-of-the-art reasoning models on five competition-level benchmarks and achieves 49.6% accuracy on AIME 2024. Furthermore, FastCuRL-1.5B-Preview surpasses DeepScaleR-1.5B-Preview on five benchmarks while only using a single node with 8 GPUs and a total of 50% of training steps.