# Train Long, Think Short: Curriculum Learning for Efficient Reasoning

arXiv: https://arxiv.org/abs/2508.08940 · HTML: https://mlsanity.com/paper/2508.08940/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning.
- Builds on 19 of its 26 references that are in the map.
- First posted on arXiv 12 Aug 2025.

## Placed in

- LLM reasoning / [Test-time compute and efficient thinking](https://mlsanity.com/lr/test-time-compute-and-efficient-thinking/)

## Builds on (most cited first, 19 of 19)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning](https://mlsanity.com/paper/2501.12948/) (2025)
- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [s1: Simple test-time scaling](https://mlsanity.com/paper/2501.19393/) (2025)
- [Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models](https://mlsanity.com/paper/2503.16419/) (2025)
- [L1: Controlling How Long A Reasoning Model Thinks With Reinforcement Learning](https://mlsanity.com/paper/2503.04697/) (2025)
- [Chain of Draft: Thinking Faster by Writing Less](https://mlsanity.com/paper/2502.18600/) (2025)
- [Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models](https://mlsanity.com/paper/2408.00724/) (2024)
- [TokenSkip: Controllable Chain-of-Thought Compression in LLMs](https://mlsanity.com/paper/2502.12067/) (2025)
- [Training Language Models to Reason Efficiently](https://mlsanity.com/paper/2502.04463/) (2025)
- [When More is Less: Understanding Chain-of-Thought Length in LLMs](https://mlsanity.com/paper/2502.07266/) (2025)
- [From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models](https://mlsanity.com/paper/2406.16838/) (2024)
- [C3oT: Generating Shorter Chain-of-Thought without Compromising Effectiveness](https://mlsanity.com/paper/2412.11664/) (2024)
- [Thinkless: LLM Learns When to Think](https://mlsanity.com/paper/2505.13379/) (2025)
- [Following Length Constraints in Instructions](https://mlsanity.com/paper/2406.17744/) (2024)
- [ConciseRL: Conciseness-Guided Reinforcement Learning for Efficient Reasoning Models](https://mlsanity.com/paper/2505.17250/) (2025)
- [Precise Length Control in Large Language Models](https://mlsanity.com/paper/2412.11937/) (2024)

## Built on by (most cited first, 20 of 20)

- [VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models](https://mlsanity.com/paper/2509.19803/) (2025)
- [On-policy Distillation with Verifiable Reward](https://mlsanity.com/paper/2608.24696/) (2026)
- [CLPO: Curriculum Learning meets Policy Optimization for LLM Reasoning](https://mlsanity.com/paper/2509.25004/) (2025)
- [What Makes a Good Curriculum? Disentangling the Effects of Data Ordering on LLM Mathematical Reasoning](https://mlsanity.com/paper/2510.19099/) (2025)
- [Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning](https://mlsanity.com/paper/2605.02913/) (2026)
- [Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following](https://mlsanity.com/paper/2512.23457/) (2025)
- [Neural Chain-of-Thought Search: Searching the Optimal Reasoning Path to Enhance Large Language Models](https://mlsanity.com/paper/2601.11340/) (2026)
- [Reinforcement Mid-Training](https://mlsanity.com/paper/2509.24375/) (2025)
- [GanitLLM: Difficulty-Aware Bengali Mathematical Reasoning through Curriculum-GRPO](https://mlsanity.com/paper/2601.06767/) (2026)
- [Thinking-Free Policy Initialization Makes Distilled Reasoning Models More Effective and Efficient Reasoners](https://mlsanity.com/paper/2509.26226/) (2025)
- [PuzzleCraft: Exploration-Aware Curriculum Learning for Puzzle-Based RLVR in VLMs](https://mlsanity.com/paper/2512.14944/) (2025)
- [Training-Trajectory-Aware Token Selection](https://mlsanity.com/paper/2601.10348/) (2026)
- [Concise Reasoning in the Lens of Lagrangian Optimization](https://mlsanity.com/paper/2510.10168/) (2025)
- [Learning to Reason Efficiently with Discounted Reinforcement Learning](https://mlsanity.com/paper/2510.23486/) (2025)
- [GraphDancer: Training LLMs to Explore and Reason over Graphs via Two-Stage Curriculum Post-Training](https://mlsanity.com/paper/2602.02518/) (2026)
- [Boosting LLM Reasoning via Human-Inspired Reward Shaping](https://mlsanity.com/paper/2602.04265/) (2026)
- [APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards](https://mlsanity.com/paper/2602.00760/) (2026)
- [Efficient Chain-of-Modality Reasoning via Progressive Compression for Spoken Language Models](https://mlsanity.com/paper/2607.19932/) (2026)
- [Recursive Vision Language Models for General Symbolic Reasoning](https://mlsanity.com/paper/2608.01534/) (2026)
- [Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation](https://mlsanity.com/paper/2610.09587/) (2026)

## Abstract (arXiv)

Recent work on enhancing the reasoning abilities of large language models (LLMs) has introduced explicit length control as a means of constraining computational cost while preserving accuracy. However, existing approaches rely on fixed-length training budgets, which do not take advantage of the natural progression from exploration to compression during learning. In this work, we propose a curriculum learning strategy for length-controlled reasoning using Group Relative Policy Optimization (GRPO). Our method starts with generous token budgets and gradually tightens them over training, encouraging models to first discover effective solution strategies and then distill them into more concise reasoning traces. We augment GRPO with a reward function that balances three signals: task correctness (via verifier feedback), length efficiency, and formatting adherence (via structural tags). Experiments on GSM8K, MATH500, SVAMP, College Math, and GSM+ demonstrate that curriculum-based training consistently outperforms fixed-budget baselines at the same final budget, achieving higher accuracy and significantly improved token efficiency. We further ablate the impact of reward weighting and decay schedule design, showing that progressive constraint serves as a powerful inductive bias for training efficient reasoning models. Our code and checkpoints are released at: https://github.com/hammoudhasan/curriculum_grpo.