The paper critiques the common reinforcement‑learning approach of sampling tool subsets when the full set of tools is enumerable, showing that sampling leads to degraded policy estimates and increased reward sparsity in genomic reasoning tasks. It proposes Full‑Group Policy Optimization (FGPO), which evaluates every tool subset and precomputes rewards in a table, thereby eliminating the need for frozen‑reasoner calls during training. Experiments across five frozen reasoners and three genomic benchmarks demonstrate that FGPO consistently outperforms GRPO, improving average scores by 6.75 points and reducing the number of invoked tools per question.
By Haoyue Liu, Xiaoyu Ma, Ye Chen, Zhichao Wang, Xiaoying Tang
arXiv:2607. 00531v1 Announce Type: cross Abstract: Scientific reasoning is an increasingly important capability of large language models, yet improving the robustness and efficiency of training such reasoning remains a key open challenge.
By Xuefeng Liu, Mingxuan Cao, Qinan Huang, Thomas Brettin, Rick Stevens, Le Cong
arXiv:2607. 00152v1 Announce Type: cross Abstract: Three of the most popular methods for training language models to reason look like three different tricks.
By Yong Yi Bay, Kathleen A. Yearick
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.
By Pixel Nomand, Elena Voss, Marcus Hale, Sofia Reyes
The paper investigates Evolution Strategies (ES) as a memory‑efficient post‑training method for large language model (LLM) reasoning. It demonstrates that ES outperforms Group Relative Policy Optimization (GRPO) by achieving broader reasoning coverage, improving Pass@K metrics, and avoiding entropy collapse. The study also reveals that ES’s performance gains stem from sparse, high‑magnitude parameter updates, do not cause catastrophic forgetting, and can be combined with GRPO in a sequential training strategy.
By Yunpeng Ba, Zhi Zheng, Yue Xie, Jiaqing Li, Xialiang Tong, Tao Zhong, Mingxuan Yuan, Zhichao Lu, Xuyang Wu, Zhenkun Wang
arXiv:2606. 29082v1 Announce Type: cross Abstract: Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture?
By Young-Jun Lee, Seungone Kim, Minki Kang, Alistair Cheong Liang Chuen, Zerui Chen, Seungho Han, Taehee Jung, Dongyeop Kang
arXiv:2608. 01418v1 Announce Type: cross Abstract: Autoregressive rollout generation is a major computational cost in reinforcement learning for large language models.
By Wenhao Zhang, Yibo Xie, Rui Wang, Jiahua Yang, Lei Jiang, Zibo Yang, Yawei Wang, Jiali Xu, jasperawang, Haoyang Long, Huan Xiong, alantzhao
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.
By Gijs Kassenaar, Zhao Yang, Vincent Fran\c{c}ois-Lavet
arXiv:2606. 16771v1 Announce Type: new Abstract: As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities.
By Haotian Liu, Yihao Liu, Jingwei Ni, Siyuan Huang, Xinpeng Liu, Pengyu Cheng, Jiajun Song, Ruijin Ding, Junfeng Li, Zhechao Yu, Mengyu Zhou, Hongteng Xu, Xiaoxi Jiang, Guanjun Jiang
Group Relative Policy Optimization (GRPO) is effective when the current policy already samples useful reasoning trajectories, but it stalls on hard prompts whose correct solution modes lie outside the student's on-policy support. We propose TREK (Teacher-Routed Exploration via Forward KL), a simple staged procedure that uses distillation not for imitation but for exploration support expansion.
The paper introduces F-GRPO, a method that addresses the issue of reinforcement learning policies overfitting to common trajectories while neglecting rare correct ones. By deriving the probability of prompt‑local tail‑miss events and proposing a difficulty‑aware scaling coefficient inspired by Focal loss, the authors show that down‑weighting high‑success sampled groups can improve performance. Experiments on categorical simulations, Maze, and large language models (Qwen2.5‑7B) demonstrate that F‑GRPO raises average math pass rates and out‑of‑distribution performance without increasing group size or computational cost.
By Daniil Plyusov, Alexey Gorbatovski, Boris Shaposhnikov, Viacheslav Sinii, Alexey Malakhov, Daria Korotyshova, Daniil Gavrilov
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.
By Zhanke Zhou, Xiangyu Lu, Chentao Cao, Brando Miranda, Tongliang Liu, Bo Han, Sanmi Koyejo