Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning

• URL: http://arxiv.org/abs/2502.06781v1
• Date: Mon, 10 Feb 2025 18:57:29 GMT
• Title: Exploring the Limit of Outcome Reward for Learning Mathematical Reasoning
• Authors: Chengqi Lyu, Songyang Gao, Yuzhe Gu, Wenwei Zhang, Jianfei Gao, Kuikun Liu, Ziyi Wang, Shuaibin Li, Qian Zhao, Haian Huang, Weihan Cao, Jiangning Liu, Hongwei Liu, Junnan Liu, Songyang Zhang, Dahua Lin, Kai Chen,
• Abstract summary: 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.
• Score: 65.2421542320293
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Reasoning abilities, especially those for solving complex math problems, are crucial components of general intelligence. Recent advances by proprietary companies, such as o-series models of OpenAI, have made remarkable progress on reasoning tasks. However, the complete technical details remain unrevealed, and the techniques that are believed certainly to be adopted are only reinforcement learning (RL) and the long chain of thoughts. This paper proposes a new RL framework, termed OREAL, to pursue the performance limit that can be achieved through \textbf{O}utcome \textbf{RE}w\textbf{A}rd-based reinforcement \textbf{L}earning for mathematical reasoning tasks, where only binary outcome rewards are easily accessible. We theoretically prove that behavior cloning on positive trajectories from best-of-N (BoN) sampling is sufficient to learn the KL-regularized optimal policy in binary feedback environments. This formulation further implies that the rewards of negative samples should be reshaped to ensure the gradient consistency between positive and negative samples. To alleviate the long-existing difficulties brought by sparse rewards in RL, which are even exacerbated by the partial correctness of the long chain of thought for reasoning tasks, we further apply a token-level reward model to sample important tokens in reasoning trajectories for learning. With OREAL, for the first time, a 7B model can obtain 94.0 pass@1 accuracy on MATH-500 through RL, being on par with 32B models. OREAL-32B also surpasses previous 32B models trained by distillation with 95.0 pass@1 accuracy on MATH-500. Our investigation also indicates the importance of initial policy models and training queries for RL. Code, models, and data will be released to benefit future research\footnote{https://github.com/InternLM/OREAL}.

Related papers

• A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce [68.99924691391048]
  We revisit GRPO from a reinforce-like algorithm perspective and analyze its core components. We find that a simple rejection sampling baseline, RAFT, yields competitive performance than GRPO and PPO. Motivated by this insight, we propose Reinforce-Rej, a minimal extension of policy gradient that filters both entirely incorrect and entirely correct samples.
  arXiv  Detail & Related papers  (2025-04-15T16:15:02Z)
• 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)
• LLMs Can Easily Learn to Reason from Demonstrations Structure, not content, is what matters! [53.84130385074551]
  Large reasoning models (LRMs) tackle complex reasoning problems by following long chain-of-thoughts (Long CoT) We find that a Large Language model (LLM) can effectively learn Long CoT reasoning through data-efficient supervised fine-tuning (SFT) and parameter-efficient low-rank adaptation (LoRA) With just 17k long CoT training samples, the Qwen2.5-32B-Instruct model achieves significant improvements on a wide range of math and coding benchmarks.
  arXiv  Detail & Related papers  (2025-02-11T08:48:48Z)
• ACECODER: Acing Coder RL via Automated Test-Case Synthesis [36.740393665032954]
  We design a pipeline that generates extensive (question, test-cases) pairs from existing code data.<n>We construct preference pairs based on pass rates over sampled programs to train reward models with Bradley-Terry loss.<n>We show that our RL training can improve model on HumanEval-plus by over 25% and MBPP-plus by 6% for merely 80 optimization steps.
  arXiv  Detail & Related papers  (2025-02-03T18:46:04Z)
• 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)
• LMGT: Optimizing Exploration-Exploitation Balance in Reinforcement Learning through Language Model Guided Trade-offs [27.014415210732103]
  We introduce textbfLanguage textbfModel textbfGuided textbfTrade-offs (i.e., textbfLMGT), a novel, sample-efficient framework for Reinforcement Learning.
  arXiv  Detail & Related papers  (2024-09-07T07:40:43Z)
• RewardBench: Evaluating Reward Models for Language Modeling [100.28366840977966]
  We present RewardBench, a benchmark dataset and code-base for evaluation of reward models. The dataset is a collection of prompt-chosen-rejected trios spanning chat, reasoning, and safety. On the RewardBench leaderboard, we evaluate reward models trained with a variety of methods.
  arXiv  Detail & Related papers  (2024-03-20T17:49:54Z)
• Improving Large Language Models via Fine-grained Reinforcement Learning with Minimum Editing Constraint [104.53687944498155]
  Reinforcement learning (RL) has been widely used in training large language models (LLMs) We propose a new RL method named RLMEC that incorporates a generative model as the reward model. Based on the generative reward model, we design the token-level RL objective for training and an imitation-based regularization for stabilizing RL process.
  arXiv  Detail & Related papers  (2024-01-11T17:58:41Z)
• B-Pref: Benchmarking Preference-Based Reinforcement Learning [84.41494283081326]
  We introduce B-Pref, a benchmark specially designed for preference-based RL. A key challenge with such a benchmark is providing the ability to evaluate candidate algorithms quickly. B-Pref alleviates this by simulating teachers with a wide array of irrationalities.
  arXiv  Detail & Related papers  (2021-11-04T17:32:06Z)

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.