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.
arXiv:2509. 25004v2 Announce Type: replace Abstract: Online reinforcement learning with verifiable rewards (RLVR) has become an effective paradigm for improving the reasoning abilities of large language models, but most methods still optimize reasoning trajectories over the static problem set, wasting rollout budget on solved or overly difficult problems.
AdaC-GRPO introduces an adaptive curriculum learning framework for mastering long-horizon visual Sudoku puzzles, a multimodal task that challenges large language models with multi-step deductive reasoning. The authors present FG-Sudoku, a fine-grained benchmark that categorizes puzzles by grid size and required deductive steps, revealing that frontier multimodal large language models (MLLMs) struggle with complex long-range dependencies. AdaC-GRPO dynamically constructs training batches by tracking the model’s Zone of Proximal Development through online rollout accuracy, enabling Qwen2.5-VL-7B to close a significant portion of the accuracy gap to Gemini-2.5-Pro and demonstrating generalizability across other models.
Goldilocks RL proposes an adaptive data‑selection strategy for reinforcement learning in language models, using a Selector network to predict reward variability and prioritize questions that are neither too easy nor too hard. By continuously adapting to the model’s evolving abilities, Goldilocks improves training efficiency on large‑scale reasoning datasets, achieving up to 78% fewer optimization steps compared to standard GRPO. The approach addresses the sample‑inefficiency problem of sparse rewards in reasoning tasks.
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.
The paper introduces Policy-Compatible Reinforcement Learning (PICO), a method that addresses the learning cliff in reinforcement learning with verifiable rewards (RLVR) by performing distribution-constrained joint decoding. PICO guides token-level decoding with expert data while preserving the model’s token probabilities, and uses a dynamic top‑k mechanism to keep sampling within a finite divergence budget. The resulting trajectories are verified and policy‑compatible, and are jointly optimized with on‑policy rollouts using a mixed‑behavior objective that mitigates distribution mismatch via importance sampling, leading to consistent performance gains over standard RLVR and prior off‑policy baselines on diverse reasoning datasets and agentic benchmarks.
arXiv:2609.39321v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has emerged as a memory-efficient reinforcement fine-tuning (RFT) technique for reasoning-intensive tasks....
arXiv:2606. 01281v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models (LLMs).
arXiv:2607. 27610v1 Announce Type: new Abstract: Reinforcement learning (RL) finetuning significantly enhances the reasoning capabilities of large language models (LLMs), yet its effectiveness critically depends on selecting prompts of appropriate difficulty for the current policy.
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:2608. 20256v1 Announce Type: new Abstract: Reasoning language models trained with reinforcement learning typically operate under a fixed token budget rather than an explicitly adaptive one, which can lead to over-computation on easy problems and insufficient computation on difficult ones.
The paper investigates how curriculum difficulty progression affects training in Group Relative Policy Optimization (GRPO). It finds that continually selecting medium‑difficulty samples is not optimal; a staged curriculum that gradually shifts toward harder samples improves performance, reaching a peak accuracy of 0.6591. However, progressing too far to very hard samples degrades accuracy, indicating a non‑monotonic benefit of difficulty progression.
arXiv:2605. 21125v2 Announce Type: replace Abstract: Group Relative Policy Optimization (GRPO), a prominent algorithm within the Reinforcement Learning from Verifiable Rewards (RLVR) framework, has achieved strong results in improving the reasoning capabilities of large language models (LLMs).