mlsanityData to 14 Oct 2026

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

arXiv 2503.17287 ↗First posted 21 Mar 2025cs.CLcited by 27

On the map: LLM reasoning → Reinforcement learning for reasoning

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.

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.

Builds on

11 of 23 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scale18 Mar

Other references · 10

  1. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  2. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  3. 2024Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameterscited by 1,986
  4. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  5. 2025s1: Simple test-time scalingcited by 1,341
  6. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  7. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
  8. 2025Demystifying Long Chain-of-Thought Reasoning in LLMscited by 326
  9. 2025rStar-Math: Small LLMs Can Master Math Reasoning with Self-Evolved Deep Thinkingcited by 313
  10. 2024Imitate, Explore, and Self-Improve: A Reproduction Report on Slow-thinking Reasoning Systemscited by 164

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 15; 2026: 12.

27 papers.

Sort:

By area:

  1. 2025JustRL: Scaling a 1.5B LLM with a Simple RL Recipecited by 64
  2. 2025RLinf: Flexible and Efficient Large-scale Reinforcement Learning via Macro-to-Micro Flow Transformationcited by 57
  3. 2025Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?cited by 52
  4. 2025Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVRcited by 39
  5. 2025Stable Reinforcement Learning for Efficient Reasoningcited by 27
  6. 2025CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMscited by 19
  7. 2026Does Your Reasoning Model Implicitly Know When to Stop Thinking?cited by 19
  8. 2025Feature Extraction and Steering for Enhanced Chain-of-Thought Reasoning in Language Modelscited by 13
  9. 2025CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoningcited by 13
  10. 2025Scheduling Your LLM Reinforcement Learning with Reasoning Treescited by 12
  11. 2025From Data-Centric to Sample-Centric: Enhancing LLM Reasoning via Progressive Optimizationcited by 10
  12. 2025Tiny Model, Big Logic: Diversity-Driven Optimization Elicits Large-Model Reasoning Ability in VibeThinker-1.5Bcited by 8
15 more
  1. 2026Prompt replay: speeding up grpo with on-policy reuse of high-signal promptscited by 8
  2. 2025Hunyuan-MT Technical Reportcited by 7
  3. 2025Generative Adversarial Reasoner: Enhancing LLM Reasoning with Adversarial Reinforcement Learningcited by 6
  4. 2026RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoningcited by 5
  5. 2025Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities Through Evaluation Designcited by 3
  6. 2025Enhancing Math Reasoning in Small-sized LLMs via Preview Difficulty-Aware Interventioncited by 3
  7. 2026R^3: Replay, Reflection, and Ranking Rewards for LLM Reinforcement Learningcited by 2
  8. 2026TACLer: Tailored Curriculum Reinforcement Learning for Efficient Reasoningcited by 2
  9. 2026LEEPS: Latent-Guided Explore-Exploit Prompt Sampling for Efficient RLVR in Large Language Modelscited by 2
  10. 2026ETR: Outcome-Guided Elastic Trust Regions for Policy Optimizationcited by 1
  11. 2026MathMixup: Boosting LLM Mathematical Reasoning with Difficulty-Controllable Data Synthesis and Curriculum Learningcited by 1
  12. 2026Divide-and-Conquer CoT: RL for Reducing Latency via Parallel Reasoningcited by 1
  13. 2026Batched Contextual Reinforcement: A Task-Scaling Law for Efficient Reasoningcited by 0
  14. 2026HiFloat4 Format for End-To-End Reinforcement Learning Post-Training of Large Language Modelscited by 0
  15. 2026What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori Signalscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026SortedRL: Accelerating RL Training for LLMs through Online Length-Aware Scheduling
  2. 2025Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
  3. 2026CoScale-RL: Efficient Post-Training by Co-Scaling Data and Computation
  4. 2025QwenLong-L1: Towards Long-Context Large Reasoning Models with Reinforcement Learning
  5. 2025RedStar: Does Scaling Long-CoT Data Unlock Better Slow-Reasoning Systems?
  6. 2025ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
  7. 2025The Art of Scaling Reinforcement Learning Compute for LLMs
  8. 2026Curriculum Reinforcement Learning Can Incentivize Reasoning Capacity in LLMs Beyond the Base Model