The paper introduces AdaRoll-GRPO, a method that allocates rollout budgets adaptively during Group Relative Policy Optimization (GRPO) training for large language models. By modeling rollout allocation as a Bayes‑adaptive Markov decision process, the approach learns an offline policy that assigns more rollouts to difficult questions and fewer to easier ones, all while keeping the total budget fixed. Experiments across several reasoning datasets and LLM architectures show that this adaptive strategy consistently improves GRPO training performance compared to the uniform allocation used in standard GRPO.
arXiv:2606. 07950v1 Announce Type: new Abstract: RL with verifiable rewards can substantially improve LLM reasoning, yet standard GRPO-style training often treats easy, hard, and learnable questions alike through uniform sampling and weighting, leading to inefficient compute allocation.
arXiv:2606. 05606v1 Announce Type: new Abstract: LLM post-training often relies on reinforcement learning methods that sample multiple rollouts per prompt, yet most existing approaches use a fixed rollout budget for every prompt, despite large differences in the training signal different prompts provide.
arXiv:2610.34951v1 Announce Type: cross Abstract: Recent methods for Reinforcement Learning with Verifiable Rewards (RLVR) use rollout diversity to improve reasoning performance or training efficienc...
arXiv:2605.27293v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards has become a standard recipe for improving the reasoning abilities of large language models. Existin...
The paper introduces CLOSEDLOOPGAUSSIAN, an adaptive curriculum strategy for Group Relative Policy Optimization (GRPO) that dynamically adjusts the pace and spread of an Easy-to-Hard Gaussian sampler based on probe estimates of per-difficulty accuracy. Unlike fixed easy-to-hard schedules, the method accelerates training when the model outpaces a reference curriculum, slows it down when it lags, and broadens sampling when earlier difficulties regress, thereby keeping training focused on learnable yet challenging tasks. Experiments on symbolic arithmetic reasoning demonstrate that CLOSEDLOOPGAUSSIAN outperforms vanilla GRPO and fixed open-loop curricula, especially in intermediate-difficulty regimes where group-relative learning signals are most informative.
The paper introduces Single‑Rollout Pass@k Policy Optimization (SR‑PPO), a reinforcement learning method that uses only one rollout per prompt to train language‑model agents. SR‑PPO combines Monte Carlo token‑level advantage estimation with Pass@k gradient reweighting and an online critic for baseline and weight estimation. Experiments show that SR‑PPO achieves stable learning and performance comparable to traditional Group Relative Policy Optimization (GRPO) on reasoning and logic benchmarks, even when off‑policy drift degrades standard Pass@1 PPO.
The paper introduces FastRL, a reinforcement learning framework designed to enhance the efficiency of Group Relative Policy Optimization (GRPO) and its variants. FastRL employs an advantage-aware pruning strategy that retains high-advantage trajectories while preserving gradient diversity, and an adaptive rollout sampling mechanism that adjusts sampling scale during training based on historical pruning data. Experiments show that FastRL can be integrated into GRPO, DAPO, and GSPO, yielding a 2.07× speedup on Geometry3K and GeoQA8K-R1V and a 1.64% accuracy improvement on visual reasoning benchmarks.
arXiv:2607. 26253v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) is bottlenecked by rollout generation, yet many sampled prompts produce saturated groups (all responses correct or all incorrect) whose zero reward variance yields no policy-gradient signal.
arXiv:2603. 25184v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become essential for post-training large language models (LLMs) in reasoning tasks.
arXiv:2604. 05164v3 Announce Type: replace-cross Abstract: As LLM reasoning performance plateaus, improving inference-time compute efficiency is crucial to mitigate overthinking and long thinking traces even for simple queries.
The paper introduces AnytimeReasoner, a framework that optimizes large language models for anytime reasoning by truncating the reasoning process to fit sampled token budgets and requiring the model to summarize the answer for verification. This approach adds verifiable dense rewards, improving credit assignment in reinforcement learning. The authors also propose Budget Relative Policy Optimization (BRPO), a variance reduction technique that enhances learning robustness and efficiency, and demonstrate that their method outperforms GRPO on mathematical reasoning tasks across various budgets and prior distributions.
arXiv:2606. 10184v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) relies on the diversity of $K$ rollouts within each group; otherwise, the group-mean advantage $A^{(k)} = r^{(k)} - \mu_r$ collapses to zero.