A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce

• URL: http://arxiv.org/abs/2504.11343v2
• Date: Thu, 12 Jun 2025 06:03:24 GMT
• Title: A Minimalist Approach to LLM Reasoning: from Rejection Sampling to Reinforce
• Authors: Wei Xiong, Jiarui Yao, Yuhui Xu, Bo Pang, Lei Wang, Doyen Sahoo, Junnan Li, Nan Jiang, Tong Zhang, Caiming Xiong, Hanze Dong,
• Abstract summary: We revisit GRPO from a reinforce-like algorithm perspective and analyze its core components.<n>We find that a simple rejection sampling baseline, RAFT, yields competitive performance than GRPO and PPO.<n>Motivated by this insight, we propose Reinforce-Rej, a minimal extension of policy gradient that filters both entirely incorrect and entirely correct samples.
• Score: 68.99924691391048
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Reinforcement learning (RL) has become a prevailing approach for fine-tuning large language models (LLMs) on complex reasoning tasks. Among recent methods, GRPO stands out for its empirical success in training models such as DeepSeek-R1, yet the sources of its effectiveness remain poorly understood. In this work, we revisit GRPO from a reinforce-like algorithm perspective and analyze its core components. Surprisingly, we find that a simple rejection sampling baseline, RAFT, which trains only on positively rewarded samples, yields competitive performance than GRPO and PPO. Our ablation studies reveal that GRPO's main advantage arises from discarding prompts with entirely incorrect responses, rather than from its reward normalization. Motivated by this insight, we propose Reinforce-Rej, a minimal extension of policy gradient that filters both entirely incorrect and entirely correct samples. Reinforce-Rej improves KL efficiency and stability, serving as a lightweight yet effective alternative to more complex RL algorithms. We advocate RAFT as a robust and interpretable baseline, and suggest that future advances should focus on more principled designs for incorporating negative samples, rather than relying on them indiscriminately. Our findings provide guidance for future work in reward-based LLM post-training.

Related papers

• GRPO-CARE: Consistency-Aware Reinforcement Learning for Multimodal Reasoning [53.894789613838654]
  We introduce SEED-Bench-R1, a benchmark with complex real-world videos requiring balanced perception and reasoning.<n>Using SEED-Bench-R1, we find that standard GRPO, while improving answer accuracy, often reduces logical coherence between reasoning steps and answers, with only a 57.9% consistency rate.<n>We propose GRPO-CARE, a consistency-aware RL framework optimizing both answer correctness and reasoning coherence without explicit supervision.
  arXiv  Detail & Related papers  (2025-06-19T08:49:13Z)
• Response-Level Rewards Are All You Need for Online Reinforcement Learning in LLMs: A Mathematical Perspective [6.069069082518759]
  We study the Zero-Reward Assumption in reinforcement learning for large language models (LLMs)<n>We show that the policy gradient based on true, unknown token-level rewards can be unbiasedly estimated using only a response-level reward model.<n>We propose a new algorithm: Token-Reinforced Policy Optimization (TRePO)
  arXiv  Detail & Related papers  (2025-06-03T07:44:31Z)
• Rewarding the Unlikely: Lifting GRPO Beyond Distribution Sharpening [36.81125165911328]
  Reinforcement learning is emerging as a primary driver for improving language model reasoning capabilities.<n>We investigate whether current reinforcement learning algorithms merely sharpen the base model's distribution around problems it can already solve.<n>We show that unlikeliness reward mitigates rank bias and improves pass@$N$ across a large range of $N$ in both synthetic and real theorem proving settings.
  arXiv  Detail & Related papers  (2025-06-03T01:15:15Z)
• On-Policy RL with Optimal Reward Baseline [109.47676554514193]
  On-Policy RL with Optimal reward baseline (OPO) is a novel and simplified reinforcement learning algorithm.<n>OPO emphasizes the importance of exact on-policy training, which empirically stabilizes the training process and enhances exploration.<n>Results demonstrate OPO's superior performance and training stability without additional models or regularization terms.
  arXiv  Detail & Related papers  (2025-05-29T15:58:04Z)
• On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization [52.76330545825083]
  Reinforcement learning (RL) has become popular in enhancing the reasoning capabilities of large language models (LLMs)<n>We identify a previously unrecognized phenomenon we term Lazy Likelihood Displacement (LLD), wherein the likelihood of correct responses marginally increases or even decreases during training.<n>We develop a method called NTHR, which downweights penalties on tokens contributing to the LLD. Unlike prior DPO-based approaches, NTHR takes advantage of GRPO's group-based structure, using correct responses as anchors to identify influential tokens.
  arXiv  Detail & Related papers  (2025-05-24T18:58:51Z)
• GPG: A Simple and Strong Reinforcement Learning Baseline for Model Reasoning [17.544255491384046]
  We propose a minimalist RL approach termed Group Policy Gradient (GPG) Unlike conventional methods, GPG directly optimize the original RL objective, thus obviating the need for surrogate loss functions. Our approach achieves superior performance without relying on auxiliary techniques or adjustments.
  arXiv  Detail & Related papers  (2025-04-03T12:53:41Z)
• Enhancing LLM Reasoning with Iterative DPO: A Comprehensive Empirical Investigation [29.579349371114702]
  Direct Preference Optimization (DPO) is a cost-effective alternative to reinforcement learning (RL) for large language models (LLMs)<n>We show that a single round of DPO with coarse filtering significantly enhances mathematical reasoning performance.<n>With simple verifiable rewards, our model achieves RL-level performance with significantly lower computational overhead.
  arXiv  Detail & Related papers  (2025-03-17T06:28:25Z)
• Entropy-Regularized Process Reward Model [30.279394036823092]
  Large language models (LLMs) have shown promise in performing complex multi-step reasoning, yet they continue to struggle with mathematical reasoning. We propose an entropy-regularized process reward model (ER-PRM) that integrates KL-regularized Markov Decision Processes (MDP) Our empirical experiments on the MATH and GSM8K benchmarks demonstrate that ER-PRM consistently outperforms existing process reward models.
  arXiv  Detail & Related papers  (2024-12-15T01:09:23Z)
• VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment [66.80143024475635]
  We propose VinePPO, a straightforward approach to compute unbiased Monte Carlo-based estimates. We show that VinePPO consistently outperforms PPO and other RL-free baselines across MATH and GSM8K datasets.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer [52.09480867526656]
  We identify the source of misalignment as a form of distributional shift and uncertainty in learning human preferences. To mitigate overoptimization, we first propose a theoretical algorithm that chooses the best policy for an adversarially chosen reward model. Using the equivalence between reward models and the corresponding optimal policy, the algorithm features a simple objective that combines a preference optimization loss and a supervised learning loss.
  arXiv  Detail & Related papers  (2024-05-26T05:38:50Z)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)
• Direct Preference Optimization: Your Language Model is Secretly a Reward Model [119.65409513119963]
  We introduce a new parameterization of the reward model in RLHF that enables extraction of the corresponding optimal policy in closed form. The resulting algorithm, which we call Direct Preference Optimization (DPO), is stable, performant, and computationally lightweight. Our experiments show that DPO can fine-tune LMs to align with human preferences as well as or better than existing methods.
  arXiv  Detail & Related papers  (2023-05-29T17:57:46Z)
• Provable Reward-Agnostic Preference-Based Reinforcement Learning [61.39541986848391]
  Preference-based Reinforcement Learning (PbRL) is a paradigm in which an RL agent learns to optimize a task using pair-wise preference-based feedback over trajectories. We propose a theoretical reward-agnostic PbRL framework where exploratory trajectories that enable accurate learning of hidden reward functions are acquired.
  arXiv  Detail & Related papers  (2023-05-29T15:00:09Z)

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.