Train Long, Think Short: Curriculum Learning for Efficient Reasoning

• URL: http://arxiv.org/abs/2508.08940v1
• Date: Tue, 12 Aug 2025 13:48:03 GMT
• Title: Train Long, Think Short: Curriculum Learning for Efficient Reasoning
• Authors: Hasan Abed Al Kader Hammoud, Kumail Alhamoud, Abed Hammoud, Elie Bou-Zeid, Marzyeh Ghassemi, Bernard Ghanem,
• Abstract summary: We propose a curriculum learning strategy for length-controlled reasoning.<n>Our method starts with generous token budgets and gradually tightens them over training.<n>Experiments on GSM8K, MATH500, SVAMP, College Math, and GSM+ demonstrate that curriculum-based training consistently outperforms fixed-budget baselines.
• Score: 51.506559652495476
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• The Art of Efficient Reasoning: Data, Reward, and Optimization [20.542546956993363]
  Large Language Models (LLMs) benefit from scaled Chain-of-Thought (CoT) reasoning, but also suffer from heavy computational overhead.<n> efficient reasoning aims to incentivize short yet accurate thinking trajectories, typically through reward shaping with Reinforcement Learning (RL)<n>We conduct extensive experiments (about 0.2 million GPU hours) in a unified protocol, deconstructing training prompts and rollouts, reward shaping, and optimization strategies.
  arXiv  Detail & Related papers  (2026-02-24T14:28:16Z)
• $\mathbf{T^3}$: Reducing Belief Deviation in Reinforcement Learning for Active Reasoning [25.588308192160685]
  We propose to track the deviation of model beliefs and develop $mathbfT3$, a simple yet effective method that detects excessive belief deviation and truncates trajectories during training to remove uninformative tails.<n>$mathbfT3$ consistently enhances training stability, token efficiency, and final performance, achieving up to 30% gains while cutting rollout tokens by roughly 25%.
  arXiv  Detail & Related papers  (2025-10-14T08:14:49Z)
• HINT: Helping Ineffective Rollouts Navigate Towards Effectiveness [49.72591739116668]
  Reinforcement Learning (RL) has become a key driver for enhancing the long chain-of-thought (CoT) reasoning capabilities of Large Language Models (LLMs)<n>However, prevalent methods like GRPO often fail when task difficulty exceeds the model's capacity, leading to reward sparsity and inefficient training.<n>We propose HINT: Helping Ineffective rollouts Navigate Towards effectiveness, an adaptive hinting framework.
  arXiv  Detail & Related papers  (2025-10-10T13:42:03Z)
• Recycling Pretrained Checkpoints: Orthogonal Growth of Mixture-of-Experts for Efficient Large Language Model Pre-Training [70.60554423630803]
  We propose to recycle pretrained checkpoints by expanding their parameter counts and continuing training.<n>We scale our approach to models with 70B parameters and over 1T training tokens, achieving 10.66% accuracy gain over training from scratch.
  arXiv  Detail & Related papers  (2025-10-09T09:45:45Z)
• Thinking Augmented Pre-training [88.04395622064708]
  Thinking augmented Pre-Training is a universal methodology that augments text with automatically generated thinking trajectories.<n>This paper introduces a simple and scalable approach to improve the data efficiency of large language model (LLM) training by augmenting existing text data with thinking trajectories.
  arXiv  Detail & Related papers  (2025-09-24T14:45:13Z)
• Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training [121.5858973157225]
  We investigate the effects of prolonged reinforcement learning on a small language model across a diverse set of reasoning domains.<n>We introduce controlled KL regularization, clipping ratio, and periodic reference policy resets as critical components for unlocking long-term performance gains.<n>Our model achieves significant improvements over strong baselines, including +14.7% on math, +13.9% on coding, and +54.8% on logic puzzle tasks.
  arXiv  Detail & Related papers  (2025-07-16T17:59:24Z)
• Curriculum Reinforcement Learning from Easy to Hard Tasks Improves LLM Reasoning [52.32193550674408]
  We aim to improve the reasoning capabilities of language models via reinforcement learning (RL)<n>We propose to schedule tasks from easy to hard (E2H), allowing LLMs to build reasoning skills gradually.<n>E2H Reasoner significantly improves the reasoning ability of small LLMs (1.5B to 3B)
  arXiv  Detail & Related papers  (2025-06-07T02:41:54Z)
• Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models [45.33952788910874]
  TON is a two-stage training strategy for vision-language models.<n>It introduces a think-or-not format that serves as a cold start for selective reasoning.<n>TON can reduce the completion length by up to 90% compared to vanilla GRPO.
  arXiv  Detail & Related papers  (2025-05-22T16:13:29Z)
• Self-Evolving Curriculum for LLM Reasoning [108.23021254812258]
  Self-Evolving Curriculum (SEC) is an automatic curriculum learning method that learns a curriculum policy concurrently with the RL fine-tuning process.<n>Our experiments demonstrate that SEC significantly improves models' reasoning capabilities, enabling better generalization to harder, out-of-distribution test problems.
  arXiv  Detail & Related papers  (2025-05-20T23:17:15Z)
• Rational Metareasoning for Large Language Models [17.479428400594028]
  Being prompted to engage in reasoning has emerged as a core technique for using large language models (LLMs)<n>This work introduces a novel approach based on computational models of metareasoning used in cognitive science.<n>We develop a reward function that incorporates the Value of Computation by penalizing unnecessary reasoning.
  arXiv  Detail & Related papers  (2024-10-07T23:48:52Z)
• MC-BERT: Efficient Language Pre-Training via a Meta Controller [96.68140474547602]
  Large-scale pre-training is computationally expensive. ELECTRA, an early attempt to accelerate pre-training, trains a discriminative model that predicts whether each input token was replaced by a generator. We propose a novel meta-learning framework, MC-BERT, to achieve better efficiency and effectiveness.
  arXiv  Detail & Related papers  (2020-06-10T09:22:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.