Understanding R1-Zero-Like Training: A Critical Perspective

• URL: http://arxiv.org/abs/2503.20783v1
• Date: Wed, 26 Mar 2025 17:59:14 GMT
• Title: Understanding R1-Zero-Like Training: A Critical Perspective
• Authors: Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, Min Lin,
• Abstract summary: We critically examine R1-Zero-like training by analyzing its two core components: base models and RL.<n>We investigate a wide range of base models, including DeepSeek-V3-Base, to understand how pretraining characteristics influence RL performance.<n>We present a minimalist R1-Zero recipe that achieves 43.3% accuracy on AIME 2024 with a 7B base model.
• Score: 38.515771096651356
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: DeepSeek-R1-Zero has shown that reinforcement learning (RL) at scale can directly enhance the reasoning capabilities of LLMs without supervised fine-tuning. In this work, we critically examine R1-Zero-like training by analyzing its two core components: base models and RL. We investigate a wide range of base models, including DeepSeek-V3-Base, to understand how pretraining characteristics influence RL performance. Our analysis reveals that DeepSeek-V3-Base already exhibit ''Aha moment'', while Qwen2.5 base models demonstrate strong reasoning capabilities even without prompt templates, suggesting potential pretraining biases. Additionally, we identify an optimization bias in Group Relative Policy Optimization (GRPO), which artificially increases response length (especially for incorrect outputs) during training. To address this, we introduce Dr. GRPO, an unbiased optimization method that improves token efficiency while maintaining reasoning performance. Leveraging these insights, we present a minimalist R1-Zero recipe that achieves 43.3% accuracy on AIME 2024 with a 7B base model, establishing a new state-of-the-art. Our code is available at https://github.com/sail-sg/understand-r1-zero.

Related papers

• SEAL: Steerable Reasoning Calibration of Large Language Models for Free [58.190800043449336]
  Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism. Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance. We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
  arXiv  Detail & Related papers  (2025-04-07T02:42:07Z)
• Improved Visual-Spatial Reasoning via R1-Zero-Like Training [18.61987706753493]
  Video visual-spatial intelligence (VSI) emerges as one of the most pivotal reasoning capabilities of multi-modal large language models (MLLMs) This work conducts a first, in-depth study on improving the visualspatial reasoning of MLLMs via R1-Zero-like training.
  arXiv  Detail & Related papers  (2025-04-01T15:11:11Z)
• Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model [47.108822717757945]
  We introduce Open-Reasoner-Zero, the first open source implementation of large-scale reasoning-oriented RL training. In the spirit of open source, we release our source code, parameter settings, training data, and model weights across various sizes.
  arXiv  Detail & Related papers  (2025-03-31T16:36:05Z)
• SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild [46.25416990387885]
  Long chain-of-thought (CoT) reasoning can naturally emerge through a simple reinforcement learning framework with rule-based rewards.<n>We investigate zero RL training across 10 diverse base models including LLama3-8B, Mistral-7B/24B, DeepSeek-Math-7B, Qwen2.5-math-7B, and all Qwen2.5 models from 0.5B to 32B.
  arXiv  Detail & Related papers  (2025-03-24T17:06:10Z)
• R1-Zero's "Aha Moment" in Visual Reasoning on a 2B Non-SFT Model [70.77691645678804]
  We present the first successful replication of emergent characteristics for multimodal reasoning on only a non-SFT 2B model.<n>Our model achieves 59.47% accuracy on CVBench, outperforming the base model by approximately 30% and exceeding both SFT setting by 2%.<n>In addition, we share our failed attempts and insights in attempting to achieve R1-like reasoning using RL with instruct models.
  arXiv  Detail & Related papers  (2025-03-07T04:21:47Z)
• An Empirical Study on Eliciting and Improving R1-like Reasoning Models [90.52239241349504]
  scaling RL training has become a central technique for implementing such reasoning models.<n>We demonstrate that our RL training approach consistently improves the Qwen2.5-32B base models.<n>We also explore the use of tool manipulation, finding that it significantly boosts the reasoning performance of large reasoning models.
  arXiv  Detail & Related papers  (2025-03-06T15:34:27Z)
• Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning [65.2421542320293]
  Reasoning abilities are crucial components of general intelligence.<n>Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning tasks.<n>This paper proposes a new RL framework, termed OREAL, to pursue the performance limit that can be achieved through textbfOutcome textbfREwtextbfArd-based reinforcement textbfLearning for mathematical reasoning tasks.
  arXiv  Detail & Related papers  (2025-02-10T18:57:29Z)
• Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling [52.34735382627312]
  Large language models (LLMs) have demonstrated remarkable capabilities in complex reasoning tasks.<n>Existing approaches mainly rely on imitation learning and struggle to achieve effective test-time scaling.<n>We present T1 to scale reinforcement learning by encouraging exploration and understand inference scaling.
  arXiv  Detail & Related papers  (2025-01-20T18:33:33Z)
• DeepZero: Scaling up Zeroth-Order Optimization for Deep Model Training [33.11416096294998]
  Zeroth-order (ZO) optimization has become a popular technique for solving machine learning (ML) problems. No prior work has demonstrated the effectiveness of ZO optimization in training deep neural networks (DNNs) without a significant decrease in performance. We develop DeepZero, a principled ZO deep learning (DL) framework that can scale ZO optimization to DNN training from scratch.
  arXiv  Detail & Related papers  (2023-10-03T13:05:36Z)

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.