Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

• URL: http://arxiv.org/abs/2503.24290v2
• Date: Sat, 05 Jul 2025 09:01:04 GMT
• Title: Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
• Authors: Jingcheng Hu, Yinmin Zhang, Qi Han, Daxin Jiang, Xiangyu Zhang, Heung-Yeung Shum,
• Abstract summary: We introduce Open-Reasoner-Zero, the first open source implementation of large-scale reasoning-oriented RL training on the base model.<n>We demonstrate that PPO with GAE and straightforward rule-based rewards, without any KL regularization, is sufficient to scale up both benchmark performance and response length.
• Score: 47.108822717757945
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We introduce Open-Reasoner-Zero, the first open source implementation of large-scale reasoning-oriented RL training on the base model focusing on scalability, simplicity and accessibility. Through extensive experiments, we demonstrate that a minimalist approach, vanilla PPO with GAE ($\lambda=1$, $\gamma=1$) and straightforward rule-based rewards, without any KL regularization, is sufficient to scale up both benchmark performance and response length, replicating the scaling phenomenon observed in DeepSeek-R1-Zero. Using the same base model, Qwen2.5-32B base, as DeepSeek-R1-Zero-Qwen-32B, our implementation achieves superior performance across AIME2024, MATH500, and GPQA Diamond, while demonstrating remarkable efficiency, requiring only 1/10 of the training steps compared to the DeepSeek-R1-Zero pipeline. Moreover, our analysis not only covers training dynamics and ablation for critical design choices, but also quantitatively shows how the learned critic in Reasoner-Zero training effectively identifies and devalues repetitive response patterns, yielding more robust advantage estimations and enhancing training stability. Embracing the principles of open-source, we release our source code, training data, and various model weights, fostering reproducibility and encouraging further exploration of the properties of related models.

Related papers

• DINO-R1: Incentivizing Reasoning Capability in Vision Foundation Models [18.06361678575107]
  We propose textbfDINO-R1, the first attempt to incentivize visual in-context reasoning capabilities of vision foundation models.<n>DINO-R1 introduces textbfGroup Relative Query Optimization (GRQO), a novel reinforcement-style training strategy.<n>Experiments on COCO, LVIS, and ODinW demonstrate that DINO-R1 significantly outperforms supervised fine-tuning baselines.
  arXiv  Detail & Related papers  (2025-05-29T21:58:06Z)
• AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning [50.02117478165099]
  We show that large-scale reinforcement learning can significantly enhance the reasoning capabilities of strong, small- and mid-sized models.<n>We propose a simple yet effective approach: first training on math-only prompts, then on code-only prompts.
  arXiv  Detail & Related papers  (2025-05-22T08:50:47Z)
• SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM [18.275547804539016]
  Two-Staged history-Resampling Policy optimization surpasses the performance of DeepSeek-R1-Zero-32B on the AIME24 and LiveCodeBench benchmarks. We introduce two key methodological innovations: (1) a two-stage cross-domain training paradigm designed to balance the development of mathematical reasoning and coding proficiency, and (2) History Resampling (HR), a technique to address ineffective samples.
  arXiv  Detail & Related papers  (2025-04-19T13:06:03Z)
• Understanding R1-Zero-Like Training: A Critical Perspective [38.515771096651356]
  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.
  arXiv  Detail & Related papers  (2025-03-26T17:59:14Z)
• 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)
• FastCuRL: Curriculum Reinforcement Learning with Stage-wise Context Scaling for Efficient Training R1-like Reasoning Models [28.351652568849286]
  We propose FastCuRL, a curriculum RL framework with stage-wise context scaling to achieve efficient training and concise CoT reasoning.<n>Experiment results demonstrate FastCuRL-1.5B-V3 significantly outperforms state-of-the-art reasoning models on five competition-level benchmarks.
  arXiv  Detail & Related papers  (2025-03-21T16:35:31Z)
• 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)
• START: Self-taught Reasoner with Tools [51.38785489790888]
  We introduce START (Self-Taught Reasoner with Tools), a tool-integrated long Chain-of-thought (CoT) reasoning LLM.<n> START is capable of performing complex computations, self-checking, exploring diverse methods, and self-ging.<n>It significantly outperforms the base QwQ-32B and achieves performance comparable to the state-of-the-art open-weight model R1-Distill-Qwen-32B.
  arXiv  Detail & Related papers  (2025-03-06T17:11:51Z)
• Think Inside the JSON: Reinforcement Strategy for Strict LLM Schema Adherence [0.0]
  We address the challenge of enforcing strict schema adherence in large language model (LLM) generation by leveraging reasoning capabilities.<n>Our approach trains structured reasoning skills of a 1.5B parameter model through a novel pipeline.<n>We compare our ThinkJSON approach against the original DeepSeek R1 (671B), distilled versions of DeepSeek R1 (Qwen-1.5B and Qwen-7B), and Gemini 2.0 Flash (70B)
  arXiv  Detail & Related papers  (2025-02-18T16:44:55Z)
• 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)
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning [147.16121855209246]
  We introduce our first-generation reasoning models, DeepSeek-R1-Zero and DeepSeek-R1.<n>DeepSeek-R1-Zero is trained via large-scale reinforcement learning.<n>DeepSeek-R1 incorporates multi-stage training and cold-start data before RL.
  arXiv  Detail & Related papers  (2025-01-22T15:19:35Z)
• 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)
• Model Extrapolation Expedites Alignment [135.12769233630362]
  We propose a method called ExPO to expedite alignment training with human preferences. We demonstrate that ExPO boosts a DPO model trained with only 20% steps to outperform the fully-trained one. We show that ExPO notably improves existing open-source LLMs on the leading AlpacaEval 2.0 and MT-Bench benchmarks.
  arXiv  Detail & Related papers  (2024-04-25T17:39:50Z)
• 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.