Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning

• URL: http://arxiv.org/abs/2602.14338v1
• Date: Sun, 15 Feb 2026 23:14:05 GMT
• Title: Train Less, Learn More: Adaptive Efficient Rollout Optimization for Group-Based Reinforcement Learning
• Abstract summary: Reinforcement learning (RL) plays a central role in large language model (LLM) post-training.<n>In GRPO, each query prompts the LLM to generate a group of rollouts with a fixed group size $N$.<n>When all rollouts in a group share the same outcome, either all correct or all incorrect, the group-normalized advantages become zero.<n>We introduce Adaptive Efficient Rollout Optimization (AERO), an enhancement of GRPO.
• Score: 37.10958874118462
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Reinforcement learning (RL) plays a central role in large language model (LLM) post-training. Among existing approaches, Group Relative Policy Optimization (GRPO) is widely used, especially for RL with verifiable rewards (RLVR) fine-tuning. In GRPO, each query prompts the LLM to generate a group of rollouts with a fixed group size $N$. When all rollouts in a group share the same outcome, either all correct or all incorrect, the group-normalized advantages become zero, yielding no gradient signal and wasting fine-tuning compute. We introduce Adaptive Efficient Rollout Optimization (AERO), an enhancement of GRPO. AERO uses an adaptive rollout strategy, applies selective rejection to strategically prune rollouts, and maintains a Bayesian posterior to prevent zero-advantage dead zones. Across three model configurations (Qwen2.5-Math-1.5B, Qwen2.5-7B, and Qwen2.5-7B-Instruct), AERO improves compute efficiency without sacrificing performance. Under the same total rollout budget, AERO reduces total training compute by about 48% while shortening wall-clock time per step by about 45% on average. Despite the substantial reduction in compute, AERO matches or improves Pass@8 and Avg@8 over GRPO, demonstrating a practical, scalable, and compute-efficient strategy for RL-based LLM alignment.

Related papers

• GD$^2$PO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization [54.596224644751565]
  Post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities.<n>To address this, existing methods such as Group reward-Decoupled Policy Optimization (GDPO) decompose the overall score into independent reward groups, then compute the RL loss separately within each group.<n>We propose Group-Dynamic reward-Decoupled Policy Optimization (GD$2$PO), which employs a conflict-aware filtering mechanism to mask out rollouts suffering from severe reward-wise disagreement.
  arXiv  Detail & Related papers  (2026-06-15T14:19:28Z)
• Advantage Collapse in Group Relative Policy Optimization: Diagnosis and Mitigation [13.272542054938258]
  We introduce the Advantage Collapse Rate (ACR), the first metric quantifying the proportion of training batches with ineffective gradients.<n>We then propose Adaptive Virtual Sample Policy Optimization (AVSPO), a lightweight extension of GRPO that injects virtual reward samples.<n>AVSPO reduces advantage collapse by 58-63% relative to GRPO and yields consistent accuracy gains of 4-6 percentage points across all model scales.
  arXiv  Detail & Related papers  (2026-05-20T12:57:37Z)
• Hybrid-LoRA: Bridging Full Fine-Tuning and Low-Rank Adaptation for Post-Training [5.67092968426461]
  We propose Hybrid-LoRA, an efficient hybrid post-training framework that selectively applies full fine-tuning to a small subset of modules.<n>Experiments show that Hybrid-LoRA closely matches full fine-tuning performance under a 10% full fine-tuning module budget.
  arXiv  Detail & Related papers  (2026-05-12T15:11:44Z)
• Where to Spend Rollouts: Hit-Utility Optimal Rollout Allocation for Group-Based RLVR [25.35547462790362]
  Group-based policy optimization methods typically allocate a fixed number of rollouts to every prompt.<n>We introduce hit utility, the posterior probability that at least one rollout in a proposed additional allocation for a prompt will be correct.<n>We propose Hit-Utility Optimal Rollout Allocation (HORA), a learning-free rollout allocation policy.
  arXiv  Detail & Related papers  (2026-05-08T01:42:25Z)
• Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders [74.55181072260713]
  Training with beam-search negatives consistently outperforms random negatives.<n>We introduce Windowed Partial AUC (WPAUC), which constrains the false positive rate (FPR) to a window to more directly align with Top-$K$ metrics.<n>Experiments on four real-world datasets validate the theory and deliver consistent state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-04-24T12:31:57Z)
• Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization [60.87651283510059]
  Group Relative Policy Optimization (GRPO) effectively scales LLM reasoning but incurs prohibitive computational costs.<n>We propose Dynamic Pruning Policy Optimization (DPPO), a framework that enables dynamic pruning while preserving unbiased gradient estimation.<n>To mitigate the data sparsity induced by pruning, we introduce Dense Prompt Packing, a window-based greedy strategy.
  arXiv  Detail & Related papers  (2026-03-04T14:48:53Z)
• Contextual Rollout Bandits for Reinforcement Learning with Verifiable Rewards [69.74686029941881]
  Reinforcement Learning with Verifiable Rewards (RLVR) is an effective paradigm for improving the reasoning capabilities of large language models.<n>We propose a unified neural scheduling framework that adaptively selects high-value rollouts throughout training.<n>Experiments on six mathematical reasoning benchmarks demonstrate consistent gains in performance and training efficiency across multiple RLVR optimization methods.
  arXiv  Detail & Related papers  (2026-02-09T10:51:58Z)
• Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning [45.86058898829962]
  Multi-Ad Distributionally Robust Optimization (GDRO) is an optimization-first framework that moves beyond uniform reasoning.<n>We propose two independent GDRO games for post-training: Prompt-GDRO, which employs an EMA-debiased multiplicative-weight bandit sampler to target the intensive difficulty margin and upweight persistently hard groups without frequency bias; and Rollout-GDRO, which uses a shadow-price controller to reallocate rollouts across groups, maximizing gradient variance reduction on hard tasks under a fixed mean budget (compute-neutral)<n>We validate our framework on the DAPO 14.1k dataset using Q
  arXiv  Detail & Related papers  (2026-01-27T07:10:41Z)
• Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse [43.07257245849851]
  We propose a sampling efficient RLVR algorithm that introduces two novel techniques: adaptive rollout and response reuse.<n>AR3PO consistently outperforms GRPO and matches or surpasses DAPO.<n>On the larger 32B model, AR3PO achieves comparable performance to DAPO at similar training steps while maintaining substantially lower rollout cost.
  arXiv  Detail & Related papers  (2025-09-30T05:29:53Z)
• Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay [69.67914133280296]
  Reinforcement learning (RL) has become an effective approach for fine-tuning large language models (LLMs)<n>We propose two techniques to improve data efficiency in LLM RL fine-tuning: difficulty-targeted online data selection and rollout replay.<n>Our method reduces RL fine-tuning time by 23% to 62% while reaching the same level of performance as the original GRPO algorithm.
  arXiv  Detail & Related papers  (2025-06-05T17:55:43Z)
• Group-in-Group Policy Optimization for LLM Agent Training [17.243181792126563]
  Group-in-Group Policy Optimization (GiGPO) is a novel RL algorithm that achieves fine-grained credit assignment for LLM agents.<n>We evaluate GiGPO on challenging agent benchmarks, including ALFWorld and WebShop, as well as tool-integrated reasoning on search-augmented QA tasks.
  arXiv  Detail & Related papers  (2025-05-16T08:26:59Z)
• Kalman Filter Enhanced GRPO for Reinforcement Learning-Based Language Model Reasoning [11.157278744897427]
  Group Relative Policy Optimization ( GRPO) was proposed to compute the advantage for each output by subtracting the mean reward, as the baseline, for all outputs in the group.<n>We show that using a more adaptive advantage estimation model, KRPO can improve the stability and performance of GRPO.
  arXiv  Detail & Related papers  (2025-05-12T13:09:49Z)
• Token-Efficient RL for LLM Reasoning [0.02488650627593658]
  We propose reinforcement learning strategies tailored for reasoning in large language models (LLMs) under strict memory and compute limits.<n>Building on early policy gradient methods with baseline subtraction, we design critic-free methods that operate on a small, informative subset of output tokens.<n>We show that our methods raise accuracy on the SVAMP benchmark from 46% to over 70% and show strong performance on multi-digit multiplication.
  arXiv  Detail & Related papers  (2025-04-29T14:58:43Z)
• LoRA Done RITE: Robust Invariant Transformation Equilibration for LoRA Optimization [78.93425154518705]
  Low-rank adaption (LoRA) is a widely used parameter-efficient finetuning method for LLM that reduces memory requirements.<n>This paper introduces LoRA-RITE, a novel adaptive matrix preconditioning method for LoRA optimization.
  arXiv  Detail & Related papers  (2024-10-27T22:57:12Z)
• 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)

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.