Reinforcement Learning for Reasoning in Large Language Models with One Training Example

• URL: http://arxiv.org/abs/2504.20571v3
• Date: Fri, 24 Oct 2025 10:02:36 GMT
• Title: Reinforcement Learning for Reasoning in Large Language Models with One Training Example
• Authors: Yiping Wang, Qing Yang, Zhiyuan Zeng, Liliang Ren, Liyuan Liu, Baolin Peng, Hao Cheng, Xuehai He, Kuan Wang, Jianfeng Gao, Weizhu Chen, Shuohang Wang, Simon Shaolei Du, Yelong Shen,
• Abstract summary: We show that reinforcement learning with verifiable reward using one training example (1-shot RLVR) is effective in incentivizing the math reasoning capabilities of large language models (LLMs)<n>We identify some interesting phenomena during 1-shot RLVR, including cross-category generalization, increased frequency of self-reflection, and sustained test performance improvement.
• Score: 117.86853102104256
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We show that reinforcement learning with verifiable reward using one training example (1-shot RLVR) is effective in incentivizing the math reasoning capabilities of large language models (LLMs). Applying RLVR to the base model Qwen2.5-Math-1.5B, we identify a single example that elevates model performance on MATH500 from 36.0% to 73.6% (8.6% improvement beyond format correction), and improves the average performance across six common mathematical reasoning benchmarks from 17.6% to 35.7% (7.0% non-format gain). This result matches the performance obtained using the 1.2k DeepScaleR subset (MATH500: 73.6%, average: 35.9%), which contains the aforementioned example. Furthermore, RLVR with only two examples even slightly exceeds these results (MATH500: 74.8%, average: 36.6%). Similar substantial improvements are observed across various models (Qwen2.5-Math-7B, Llama3.2-3B-Instruct, DeepSeek-R1-Distill-Qwen-1.5B), RL algorithms (GRPO and PPO), and different math examples. In addition, we identify some interesting phenomena during 1-shot RLVR, including cross-category generalization, increased frequency of self-reflection, and sustained test performance improvement even after the training accuracy has saturated, a phenomenon we term post-saturation generalization. Moreover, we verify that the effectiveness of 1-shot RLVR primarily arises from the policy gradient loss, distinguishing it from the "grokking" phenomenon. We also show the critical role of promoting exploration (e.g., by incorporating entropy loss with an appropriate coefficient) in 1-shot RLVR training. We also further discuss related observations about format correction, label robustness and prompt modification. These findings can inspire future work on RLVR efficiency and encourage a re-examination of recent progress and the underlying mechanisms in RLVR. All resources are open source at https://github.com/ypwang61/One-Shot-RLVR.

Related papers

• Masked-and-Reordered Self-Supervision for Reinforcement Learning from Verifiable Rewards [13.064343544668283]
  We propose MR-RLVR (Masked-and-Reordered RLVR), which constructs process-level self-supervised rewards via "masked-then-fill" and "step reordering"<n>We implement MR-RLVR on Qwen2.5-3B and DeepSeek-R1-Distill-Qwen-1.5B, and evaluate on AIME24, AIME25, AMC23, and MATH500.
  arXiv  Detail & Related papers  (2025-11-21T18:23:04Z)
• Efficient Reinforcement Learning for Large Language Models with Intrinsic Exploration [33.02780998281276]
  Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning ability of large language models.<n>This study investigates how simply leveraging intrinsic data properties, almost free benefit during training, can improve data efficiency for RLVR.
  arXiv  Detail & Related papers  (2025-11-02T04:16:47Z)
• SPARK: Synergistic Policy And Reward Co-Evolving Framework [84.22494672256894]
  We introduce the Synergistic Policy And Reward Co-Evolving Framework (SPARK), an efficient, on-policy, and stable method that builds on RLVR.<n>Instead of discarding rollouts and correctness data, SPARK recycles this valuable information to simultaneously train the model itself as a generative reward model.<n>We show that SPARK achieves significant performance gains on multiple LLM and LVLM models and multiple reasoning, reward models, and general benchmarks.
  arXiv  Detail & Related papers  (2025-09-26T17:50:12Z)
• Reinforcement Learning with Rubric Anchors [26.9944158097067]
  Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs)<n>We extend the RLVR paradigm to open-ended tasks by integrating rubric-based rewards.<n>We construct, to our knowledge, the largest rubric reward system to date, with over 10,000 rubrics from humans, LLMs, or a hybrid human-LLM collaboration.
  arXiv  Detail & Related papers  (2025-08-18T10:06:08Z)
• Spurious Rewards: Rethinking Training Signals in RLVR [130.3484456088909]
  We show that reinforcement learning with verifiable rewards (RLVR) can elicit strong mathematical reasoning in certain models.<n>For example, RLVR improves MATH-500 performance for Qwen2.5-Math-7B in absolute points by 21.4%.<n>We find code reasoning -- thinking in code without actual code execution -- to be a distinctive Qwen2.5-Math behavior that becomes significantly more frequent after RLVR.
  arXiv  Detail & Related papers  (2025-06-12T17:49:55Z)
• Skywork Open Reasoner 1 Technical Report [51.403686909760914]
  We present Skywork-OR1, an effective and scalable reinforcement learning (RL) implementation for long Chain-of-Thought (CoT) models.<n>Building on the DeepSeek-R1-Distill model series, our RL approach achieves notable performance gains.<n>Our Skywork-OR1-32B model surpasses both DeepSeek-R1 and Qwen3-32B on the AIME24 and AIME25 benchmarks.
  arXiv  Detail & Related papers  (2025-05-28T12:56:04Z)
• 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)
• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining [74.83412846804977]
  Reinforcement learning (RL)-based fine-tuning has become a crucial step in post-training language models. We present a systematic end-to-end study of RL fine-tuning for mathematical reasoning by training models entirely from scratch.
  arXiv  Detail & Related papers  (2025-04-10T17:15:53Z)
• UI-R1: Enhancing Action Prediction of GUI Agents by Reinforcement Learning [31.796328505473305]
  We propose UI-R1, the first framework to explore how rule-based reinforcement learning can enhance the reasoning capabilities of multimodal large language models (MLLMs) for graphic user interface (GUI) action prediction tasks.<n> Specifically, UI-R1 introduces a novel rule-based action reward, enabling model optimization via policy-based algorithms such as Group Relative Policy Optimization (GRPO)<n>For efficient training, we curate a small yet high-quality dataset of 136 challenging tasks, encompassing five common action types on mobile devices.
  arXiv  Detail & Related papers  (2025-03-27T15:39:30Z)
• 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)
• LIMR: Less is More for RL Scaling [25.477841726836836]
  We introduce Learning Impact Measurement (LIM), an automated method to evaluate and prioritize training samples.<n>Our method achieves comparable or even superior performance using only 1,389 samples versus the full 8,523 samples dataset.<n>For reproducible research and future innovation, we are open-sourcing LIMR, including implementation of LIM, training and evaluation code, curated datasets, and trained models.
  arXiv  Detail & Related papers  (2025-02-17T15:13:29Z)
• Kimi k1.5: Scaling Reinforcement Learning with LLMs [84.2229964736678]
  We report on the training practice of Kimi k1.5, our latest multi-modal language model trained with reinforcement learning.<n>Long context scaling and improved policy optimization methods are key ingredients of our approach.<n>Our system achieves state-of-the-art reasoning performance across multiple benchmarks and modalities.
  arXiv  Detail & Related papers  (2025-01-22T02:48:14Z)
• 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)
• LiteVAR: Compressing Visual Autoregressive Modelling with Efficient Attention and Quantization [17.190984773586745]
  Current AR-based visual generation models require substantial computational resources, limiting their applicability on resource-constrained devices. We propose efficient attention mechanism and low-bit quantization method to enhance the efficiency of VAR models while maintaining performance.
  arXiv  Detail & Related papers  (2024-11-26T07:32:36Z)
• The Surprising Effectiveness of Test-Time Training for Few-Shot Learning [59.309477460893916]
  Language models (LMs) have shown impressive performance on tasks within their training distribution, but often struggle with structurally novel tasks.<n>We investigate the effectiveness of test-time training (TTT) as a mechanism for improving LMs' reasoning and few-shot learning capabilities.<n>Our findings highlight the limitations of in-context learning for novel tasks and demonstrate the potential of test-time training to enhance language model adaptability.
  arXiv  Detail & Related papers  (2024-11-11T18:59:45Z)
• Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling [37.01593605084575]
  TAS-Balanced is an efficient topic-aware query and balanced margin sampling technique. We show that our TAS-Balanced training method achieves state-of-the-art low-latency (64ms per query) results on two TREC Deep Learning Track query sets.
  arXiv  Detail & Related papers  (2021-04-14T16:49:18Z)
• How to Train Your Energy-Based Model for Regression [107.54411649704194]
  Energy-based models (EBMs) have become increasingly popular within computer vision in recent years. Recent work has applied EBMs also for regression tasks, achieving state-of-the-art performance on object detection and visual tracking. How EBMs should be trained for best possible regression performance is not a well-studied problem.
  arXiv  Detail & Related papers  (2020-05-04T17:55:01Z)

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.