The paper introduces Personalized Group Relative Policy Optimization (P‑GRPO), a new alignment framework for large language models that separates advantage estimation from immediate batch statistics. By normalizing advantages using preference‑group‑specific reward histories instead of the concurrent generation group, P‑GRPO maintains contrastive signals for distinct user preferences. Experiments across various tasks show that P‑GRPO converges faster and yields higher rewards than standard GRPO, improving alignment with heterogeneous human preferences while preserving general capabilities.
By Jialu Wang, Heinrich Peters, Asad A. Butt, Navid Hashemi, Alireza Hashemi, Pouya M. Ghari, Joseph Hoover, James Rae, Morteza Dehghani
arXiv:2606. 06080v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards is widely used for post-training reasoning models, but sparse outcome rewards make exploration difficult.
By Shota Takashiro, Soichiro Nishimori, Paavo Parmas, Yongmin Kim, Kohsei Matsutani, Gouki Minegishi, Yusuke Iwasawa, Takeshi Kojima, Yutaka Matsuo
arXiv:2606. 10528v1 Announce Type: new Abstract: Current reinforcement learning from human feedback (RLHF) methods primarily rely on scalar rewards from a trained reward model (RM).
By Guozheng Li, Xiyan Fu, Yiwen Guo
arXiv:2506. 13702v4 Announce Type: replace-cross Abstract: Single-trajectory preference optimization methods learn from datasets of ((prompt, response, reward)) tuples, offering a practical alternative to pairwise preference learning by directly leveraging scalar feedback.
By Bilal Faye, Hanane Azzag, Mustapha Lebbah
arXiv:2606. 28707v1 Announce Type: new Abstract: Critic-free reinforcement learning with verifiable rewards (RLVR), exemplified by Group Relative Policy Optimization (GRPO), avoids training a value function (critic) and reduces memory and compute overhead relative to critic-based PPO pipelines for aligning large language models.
By Yupeng Chang, Yuan Wu, Yi Chang
arXiv:2509. 22851v4 Announce Type: replace-cross Abstract: Margin-based optimization is fundamental to improving generalization and robustness in classification tasks.
By Yaswanth Chittepu, Prasann Singhal, Greg Durrett, Scott Niekum
Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models. Existing critic-free, group-relative methods estimate policy advantages from multiple rollouts, avoiding the substantial memory overhead of conventional proximal policy optimization (PPO) and achieving strong performance on long-horizon interactive tasks.
The paper introduces Best‑Practice Critic Optimization (BPCO), a stable and efficient recipe for training a critic in reinforcement learning for large language models. BPCO combines DPPO, bounded value predictions, Monte Carlo targets, unnormalized policy advantages, and length‑adaptive advantage estimation, allowing the critic to be conditioned on hidden reward information. Experiments on mathematical reasoning tasks with models from 1.5B to 30B parameters show that BPCO consistently outperforms a strong critic‑based baseline and matches or exceeds group‑based methods while sampling only one response per prompt.
By Penghui Qi, Xiangxin Zhou, Wee Sun Lee
The paper introduces Density-Aware Reward Aggregation (DARA), a method that adjusts reward weighting in multi-reward reinforcement learning based on the density of active rewards within rollout batches. By applying an inverse-square-root density correction, DARA gives more weight to less frequently active rewards, enabling faster learning of targeted behaviors. Experiments on tool calling and mathematical reasoning demonstrate that DARA achieves comparable final performance while reducing training steps by up to 26% and 65% respectively.
By Tong Zheng, Skylar Zhai, Zhan Cheng, TianMing Sha, Youling Huang, Shuo Zhou, Shaotong Qi, Jingcheng Liang, Xuwei Ding, Pengcheng Xu
Range-GRPO introduces a semi‑supervised post‑training framework that uses conformally calibrated reward ranges instead of single point scores for large language models. By comparing reward ranges pairwise within rollout groups, the method incorporates reward uncertainty into both the magnitude and direction of learning signals. Experiments show that Range‑GRPO outperforms other semi‑supervised approaches on both in‑distribution and out‑of‑distribution tasks while using fewer training resources.
By Ryunyi Lee, Kangjun Noh, Somin Kim, Heedong Kim, Kyungwoo Song
arXiv:2608. 19842v1 Announce Type: new Abstract: Agentic reinforcement learning (RL) has become a critical stage in the post-training of large language models.
By Dayang Liang, Lang Feng, Bo An, Yunlong Liu
arXiv:2606. 04807v1 Announce Type: new Abstract: Mitigating social bias in Large Language Models (LLMs) presents a distinct alignment challenge: unlike verifiable tasks, bias lacks a single ground truth, creating a high-variance, subjective reward landscape.
By Saket Reddy, Ke Yang, ChengXiang Zhai