GRPO-MA: Multi-Answer Generation in GRPO for Stable and Efficient Chain-of-Thought Training

• URL: http://arxiv.org/abs/2509.24494v2
• Date: Tue, 28 Oct 2025 07:36:45 GMT
• Title: GRPO-MA: Multi-Answer Generation in GRPO for Stable and Efficient Chain-of-Thought Training
• Authors: Hongcheng Wang, Yinuo Huang, Sukai Wang, Guanghui Ren, Hao Dong,
• Abstract summary: GRPO, a Reinforcement Learning (RL) approach, can effectively train Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) and Vision-Language Models (VLMs)<n>In this paper, we analyze three challenges of GRPO: gradient coupling between thoughts and answers, sparse reward signals caused by limited parallel sampling, and unstable advantage estimation.<n>We propose GRPO-MA, a simple yet theoretically grounded method that leverages multi-answer generation from each thought process, enabling more robust and efficient optimization.
• Score: 13.218620894749067
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent progress, such as DeepSeek-R1, has shown that the GRPO algorithm, a Reinforcement Learning (RL) approach, can effectively train Chain-of-Thought (CoT) reasoning in Large Language Models (LLMs) and Vision-Language Models (VLMs). In this paper, we analyze three challenges of GRPO: gradient coupling between thoughts and answers, sparse reward signals caused by limited parallel sampling, and unstable advantage estimation. To mitigate these challenges, we propose GRPO-MA, a simple yet theoretically grounded method that leverages multi-answer generation from each thought process, enabling more robust and efficient optimization. Theoretically, we show that the variance of thought advantage decreases as the number of answers per thought increases. Empirically, our gradient analysis confirms this effect, showing that GRPO-MA reduces gradient spikes compared to GRPO. Experiments on math, code, and diverse multimodal tasks demonstrate that GRPO-MA substantially improves performance and training efficiency. Our ablation studies further reveal that increasing the number of answers per thought consistently enhances model performance.

Related papers

• Evaluating GRPO and DPO for Faithful Chain-of-Thought Reasoning in LLMs [0.7045900712659982]
  Chain-of-thought (CoT) reasoning has emerged as a powerful technique for improving the problem-solving capabilities of large language models (LLMs)
  arXiv  Detail & Related papers  (2025-12-27T16:07:00Z)
• DaGRPO: Rectifying Gradient Conflict in Reasoning via Distinctiveness-Aware Group Relative Policy Optimization [20.66452395111739]
  We propose Distinctiveness-aware Group Relative Policy Optimization (DaGRPO)<n>DaGRPO incorporates two core mechanisms: (1) Sequence-level Gradient Rectification, which utilizes fine-grained scoring to dynamically mask sample pairs with low distinctiveness; and (2) Off-policy Data Augmentation, which introduces high-quality anchors to recover training signals for challenging tasks.<n>In-depth analysis confirms that DaGRPO effectively mitigates gradient explosion and accelerates the emergence of long-chain reasoning capabilities.
  arXiv  Detail & Related papers  (2025-12-06T07:51:36Z)
• Latent Chain-of-Thought for Visual Reasoning [53.541579327424046]
  Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs)<n>We reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference.<n>We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on seven reasoning benchmarks.
  arXiv  Detail & Related papers  (2025-10-27T23:10:06Z)
• CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs [53.749193998004166]
  Curriculum learning plays a crucial role in enhancing the training efficiency of large language models.<n>We propose CurES, an efficient training method that accelerates convergence and employs Bayesian posterior estimation to minimize computational overhead.
  arXiv  Detail & Related papers  (2025-10-01T15:41:27Z)
• EDGE-GRPO: Entropy-Driven GRPO with Guided Error Correction for Advantage Diversity [7.818698554631196]
  Group Relative Policy Optimization (GRPO) algorithm relies on sparse reward rules, leading to the advantage collapse problem.<n>We propose the EDGE-GRPO algorithm, which adopts textbfEntropy-textbfDriven Advantage and textbfGuided textbfError Correction to effectively mitigate the problem of advantage collapse.
  arXiv  Detail & Related papers  (2025-07-29T14:23:58Z)
• 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)
• 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)
• Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO [68.44918104224818]
  Autoregressive image generation presents unique challenges distinct from Chain-of-Thought (CoT) reasoning.<n>This study provides the first comprehensive investigation of the GRPO and DPO algorithms in autoregressive image generation.<n>Our findings reveal that GRPO and DPO exhibit distinct advantages, and crucially, that reward models possessing stronger intrinsic generalization capabilities potentially enhance the generalization potential of the applied RL algorithms.
  arXiv  Detail & Related papers  (2025-05-22T17:59:49Z)
• 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.<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.
  arXiv  Detail & Related papers  (2025-04-15T16:15:02Z)

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.