Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training

• URL: http://arxiv.org/abs/2507.12507v1
• Date: Wed, 16 Jul 2025 17:59:24 GMT
• Title: Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training
• Authors: Mingjie Liu, Shizhe Diao, Jian Hu, Ximing Lu, Xin Dong, Hao Zhang, Alexander Bukharin, Shaokun Zhang, Jiaqi Zeng, Makesh Narsimhan Sreedhar, Gerald Shen, David Mosallanezhad, Di Zhang, Jonas Yang, June Yang, Oleksii Kuchaiev, Guilin Liu, Zhiding Yu, Pavlo Molchanov, Yejin Choi, Jan Kautz, Yi Dong,
• Abstract summary: 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.
• Score: 121.5858973157225
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in reasoning-focused language models such as OpenAI's O1 and DeepSeek-R1 have shown that scaling test-time computation-through chain-of-thought reasoning and iterative exploration-can yield substantial improvements on complex tasks like mathematics and code generation. These breakthroughs have been driven by large-scale reinforcement learning (RL), particularly when combined with verifiable reward signals that provide objective and grounded supervision. In this report, we investigate the effects of prolonged reinforcement learning on a small language model across a diverse set of reasoning domains. Our work identifies several key ingredients for effective training, including the use of verifiable reward tasks, enhancements to Group Relative Policy Optimization (GRPO), and practical techniques to improve training stability and generalization. We introduce controlled KL regularization, clipping ratio, and periodic reference policy resets as critical components for unlocking long-term performance gains. Our model achieves significant improvements over strong baselines, including +14.7% on math, +13.9% on coding, and +54.8% on logic puzzle tasks. To facilitate continued research, we release our model publicly.

Related papers

• Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning [82.43575191712726]
  We introduce a fine-grained analytic framework to dissect the impact ofReinforcement learning on reasoning.<n>Our framework specifically investigates key elements that have been hypothesized to benefit from RL training.
  arXiv  Detail & Related papers  (2025-06-05T07:53:59Z)
• Towards Effective Code-Integrated Reasoning [89.47213509714578]
  We investigate code-integrated reasoning, where models generate code when necessary and integrate feedback by executing it through a code interpreter.<n>Tool-augmented reinforcement learning can still suffer from potential instability in the learning dynamics.<n>We develop enhanced training strategies that balance exploration and stability, progressively building tool-use capabilities while improving reasoning performance.
  arXiv  Detail & Related papers  (2025-05-30T11:30:18Z)
• 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)
• Improving RL Exploration for LLM Reasoning through Retrospective Replay [45.00643118030677]
  We propose a novel algorithm named Retrospective Replay-based Reinforcement Learning (RRL), which introduces a dynamic replay mechanism throughout the training process.<n>RRL enables the model to revisit promising states identified in the early stages, thereby improving its efficiency and effectiveness in exploration.
  arXiv  Detail & Related papers  (2025-04-19T17:40:04Z)
• Reasoning Under 1 Billion: Memory-Augmented Reinforcement Learning for Large Language Models [53.4530106173067]
  Large language models (LLMs) with reinforcement learning (RL) have shown promising improvements in complex reasoning tasks.<n>RL remains challenging for tiny LLMs with 1 billion parameters or fewer because they lack the necessary pretraining strength to explore effectively.<n>This work introduces a novel intrinsic motivation approach that leverages episodic memory to address this challenge.
  arXiv  Detail & Related papers  (2025-04-03T04:46:17Z)
• Demystifying Long Chain-of-Thought Reasoning in LLMs [46.352406501403465]
  Long chains-of-thought (CoTs) enable strategies like backtracking and error correction.<n>Reinforcement learning (RL) has emerged as a crucial method for developing these capabilities.<n>We identify the key factors that enable models to generate long CoT trajectories.
  arXiv  Detail & Related papers  (2025-02-05T17:13:32Z)
• T1: 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)

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.