paper-with-me

홈 › Papers

VCRL: Variance-based Curriculum Reinforcement Learning for Large Language Models

2025-09-24 · Guochao Jiang, Wenfeng Feng, Guofeng Quan, Chuzhan Hao, Yuewei Zhang, Guohua Liu, Hao Wang arxiv

Policy-based reinforcement learning currently plays an important role in improving LLMs on mathematical reasoning tasks. However, existing rollout-based reinforcement learning methods (GRPO, DAPO, GSPO, etc.) fail to explicitly consider LLMs' learning ability for samples of different difficulty levels, which is contrary to the human cognitive process of mathematical reasoning tasks from easy to difficult. Intuitively, we find that the variance of the rollout group's reward in RLVR partly reflects the difficulty of the current sample for LLMs. Samples that are too easy or too difficult have a lower variance, while samples with moderate difficulty have a higher variance. Based on this, we propose VCRL, a curriculum reinforcement learning framework that dynamically controls the difficulty of training samples based on the variance of group rewards. Experiments on five mathematical benchmarks and two models reveal the advantages of VCRL over the current LLM RL baselines.

📄 PDF Abstract BibTeX arXiv:2509.19803

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement LearningMathematical Reasoning

Similar Papers 제목 키워드 기반

Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills

2023-10-30 · Seongun Kim, Kyowoon Lee, Jaesik Choi

Mutual information-based reinforcement learning (RL) has been proposed as a promising framework for retrieving complex skills autonomously without a task-oriented reward function through mutual information (MI) maximizat…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)Robot Navigation

CVPO: Enhancing LLM Reinforcement Learning Reasoning via Value-Variance Adaptation and Dynamic Curriculum Learning

2026-08-04 · Ziqi Jia, Yalu Ouyang, Bo Pang, Panpan Li 외 arxiv

Reinforcement learning (RL) has emerged as an effective method for enhancing the reasoning capabilities of large language models (LLMs). However, existing methods suffer from insufficient precision in feedback on generat…

Reinforcement Learning

VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction

2026-02-13 · Xin-Qiang Cai, Masashi Sugiyama arxiv

Reinforcement Learning with Verifiable Rewards (RLVR) has emerged as a dominant paradigm for enhancing Large Language Models (LLMs) reasoning, yet its reliance on external verifiers limits its scalability. Recent finding…

Reinforcement Learning

Selector-Guided Autonomous Curriculum for One-Shot Reinforcement Learning from Verifiable Rewards

2026-05-03 · Rudray Dave, Vedang Dubey, Smit Deoghare, Sudhakar Mishra arxiv

Recently, Reinforcement Learning from Verifiable Rewards (RLVR) has been established as a highly effective technique for augmenting the math reasoning skills of Large Language Models (LLMs) based on a single instance. Cu…

Reinforcement Learning

Learning to Reason at the Frontier of Learnability

2025-02-17 · Thomas Foster, Jakob Foerster

Reinforcement learning is now widely adopted as the final stage of large language model training, especially for reasoning-style tasks such as maths problems. Typically, models attempt each question many times during a s…

Language ModelingLanguage ModellingLarge Language Modelreinforcement-learning+1