CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs

• URL: http://arxiv.org/abs/2510.01037v1
• Date: Wed, 01 Oct 2025 15:41:27 GMT
• Title: CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
• Authors: Yongcheng Zeng, Zexu Sun, Bokai Ji, Erxue Min, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Haifeng Zhang, Xu Chen, Jun Wang,
• Abstract summary: Curriculum learning plays a crucial role in enhancing the training efficiency of large language models.<n>We propose CurES, an efficient training method that accelerates convergence and employs Bayesian posterior estimation to minimize computational overhead.
• Score: 53.749193998004166
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Curriculum learning plays a crucial role in enhancing the training efficiency of large language models (LLMs) on reasoning tasks. However, existing methods often fail to adequately account for variations in prompt difficulty or rely on simplistic filtering mechanisms to select prompt datasets within a narrow criterion range, resulting in significant computational waste. In this work, we approach the problem from the perspective of reinforcement learning gradient optimization, offering a systematic and theoretical investigation into how to improve the training efficiency of LLMs. We identify two key factors influencing training efficiency: the selection of training prompts and the allocation of rollout quantities across different prompts. Our theoretical analysis reveals that the sampling distribution of prompts dictates the convergence rate of gradient descent, while the allocation of the rollout quantity influences the consistency and stability of overall gradient updates. Based on these insights, we propose CurES, an efficient training method that accelerates convergence and employs Bayesian posterior estimation to minimize computational overhead. Experiments demonstrate that our CurES outperforms Group Relative Policy Optimization (GRPO) by \textbf{+3.30} points and \textbf{+4.82} points with 1.5B and 7B models, respectively. Additionally, CurES exhibits faster convergence compared to baselines, including GRPO.

Related papers

• Data Distribution as a Lever for Guiding Optimizers Toward Superior Generalization in LLMs [60.68927774057402]
  We show, for the first time, that a lower simplicity bias induces a better generalization.<n>Motivated by this insight, we demonstrate that the training data distribution by upsampling or augmenting examples learned later in training similarly reduces SB and leads to improved generalization.<n>Our strategy improves the performance of multiple language models including Phi2-2.7B, Llama3.2-1B, Gemma3-1B-PT, Qwen3-0.6B-Base-achieving relative accuracy gains up to 18% when fine-tuned with AdamW and Muon.
  arXiv  Detail & Related papers  (2026-01-31T07:40:36Z)
• A Comedy of Estimators: On KL Regularization in RL Training of LLMs [81.7906270099878]
  reinforcement learning (RL) can substantially improve the reasoning performance of large language models (LLMs)<n>The RL objective for LLM training involves a regularization term, which is the reverse Kullback-Leibler (KL) divergence between the trained policy and the reference policy.<n>Recent works show that prevailing practices for incorporating KL regularization do not provide correct gradients for stated objectives, creating a discrepancy between the objective and its implementation.<n>We study the gradients of several estimators configurations, revealing how design choices shape gradient bias.
  arXiv  Detail & Related papers  (2025-12-26T04:20:58Z)
• Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training [76.12556589212666]
  We show that curriculum post-training avoids the exponential complexity bottleneck.<n>Under outcome-only reward signals, reinforcement learning finetuning achieves high accuracy with sample complexity.<n>We establish guarantees for test-time scaling, where curriculum-aware querying reduces both reward oracle calls and sampling cost from exponential to order.
  arXiv  Detail & Related papers  (2025-11-10T18:29:54Z)
• Prompt Curriculum Learning for Efficient LLM Post-Training [30.19003037220951]
  We introduce Prompt Curriculum Learning (PCL), an algorithm that selects intermediate-difficulty prompts using a learned value model to post-train language models.<n>We demonstrate that our value model accurately predicts prompt difficulty and allows PCL to focus on progressively more challenging prompts during RL.
  arXiv  Detail & Related papers  (2025-10-01T17:24:28Z)
• Stabilizing Policy Gradients for Sample-Efficient Reinforcement Learning in LLM Reasoning [77.92320830700797]
  Reinforcement Learning has played a central role in enabling reasoning capabilities of Large Language Models.<n>We propose a tractable computational framework that tracks and leverages curvature information during policy updates.<n>The algorithm, Curvature-Aware Policy Optimization (CAPO), identifies samples that contribute to unstable updates and masks them out.
  arXiv  Detail & Related papers  (2025-10-01T12:29:32Z)
• Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle [53.239242017802056]
  Reinforcement learning (RL) has emerged as an effective post-training paradigm for enhancing the reasoning capabilities of multimodal large language model (MLLM)<n>However, current RL pipelines often suffer from training inefficiencies caused by two underexplored issues: Advantage Collapsing and Rollout Silencing.<n>We propose Shuffle-R1, a simple yet principled framework that improves RL fine-tuning efficiency by dynamically restructuring trajectory sampling and batch composition.
  arXiv  Detail & Related papers  (2025-08-07T17:53:47Z)
• Optimal Growth Schedules for Batch Size and Learning Rate in SGD that Reduce SFO Complexity [0.6906005491572401]
  Batch-size and learning-rate scheduling in computational gradient methods can degrade efficiency and compromise convergence.<n>We theoretically derived optimal growth schedules for the batch size and learning rate that reduce SFO complexity.<n>Our results offer both theoretical insights and practical guidelines for scalable and efficient large-batch training in deep learning.
  arXiv  Detail & Related papers  (2025-08-07T11:52:25Z)
• AdaLRS: Loss-Guided Adaptive Learning Rate Search for Efficient Foundation Model Pretraining [12.630306478872043]
  We propose textbfAdaLRS, a plug-in-and-play adaptive learning rate search algorithm that conducts online optimal learning rate search.<n>Experiments show that AdaLRS adjusts suboptimal learning rates to the neighborhood of optimum with marked efficiency and effectiveness.
  arXiv  Detail & Related papers  (2025-06-16T09:14:01Z)
• Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections [65.36449542323277]
  We present a unified theoretical framework bridgingSupervised Fine-Tuning (SFT) and preference learning in Large Language Model (LLM) post-training.<n>We propose a simple yet effective learning rate reduction approach that yields significant performance improvements.
  arXiv  Detail & Related papers  (2025-06-15T05:42:29Z)
• DUMP: Automated Distribution-Level Curriculum Learning for RL-based LLM Post-training [19.701565022644605]
  We present a principled curriculum learning framework grounded in the notion of distribution-level learnability.<n>Our framework prioritizes distributions with either high average advantage (exploitation) or low sample count (exploration)<n>Our experiments show that our framework significantly improves convergence speed and final performance.
  arXiv  Detail & Related papers  (2025-04-13T20:10:27Z)
• Dynamic Loss-Based Sample Reweighting for Improved Large Language Model Pretraining [55.262510814326035]
  Existing reweighting strategies primarily focus on group-level data importance.<n>We introduce novel algorithms for dynamic, instance-level data reweighting.<n>Our framework allows us to devise reweighting strategies deprioritizing redundant or uninformative data.
  arXiv  Detail & Related papers  (2025-02-10T17:57:15Z)
• Unbiased and Efficient Self-Supervised Incremental Contrastive Learning [31.763904668737304]
  We propose a self-supervised Incremental Contrastive Learning (ICL) framework consisting of a novel Incremental InfoNCE (NCE-II) loss function. ICL achieves up to 16.7x training speedup and 16.8x faster convergence with competitive results.
  arXiv  Detail & Related papers  (2023-01-28T06:11:31Z)

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.