Harness Scaling introduces a new scaling dimension for agentic reinforcement learning by training models across diverse harness configurations instead of a single fixed harness. The approach constructs a factorized harness space, selects a compact training subset with balanced factorial coverage, and organizes cross-harness training to combine global coverage with controlled variation for the same task. Experiments across multiple benchmarks, model scales, and RL algorithms show that Harness Scaling consistently improves generalization to unseen white-box configurations and enables effective transfer to unseen external black-box harnesses.
By Fei Bai, Huatong Song, Chuan Hao, Ran Tao, Jian Yang, Bryan Dai, Wayne Xin Zhao, Ji-Rong Wen
arXiv:2610.01133v1 Announce Type: cross
Abstract: Scaling reasoning typically spends more compute on reinforcement learning (RL) or on inference. We show that a completed RL training history can yiel...
By Bangji Yang, Jiajun Fan, Hongba Ma, Ruihan Guo, Ge Liu
The paper introduces the Agentic Compositional Generalization hypothesis, suggesting that reinforcement learning (RL) primarily refines high‑level decision‑making behaviors that orchestrate pre‑trained low‑level skills, rather than teaching new domain‑specific skills from scratch. It proposes River, a training recipe that enhances reward quality by filtering low‑quality synthetic environments and adding process‑level behavior regularization. Using River, RL‑trained agents outperform other open‑source 8B models on four terminal‑agent benchmarks, achieving significant gains with fewer than 30% of the training environments.
By Yihang Yao, Bo Pang, Xuan Phi Nguyen, Ding Zhao, Shafiq Joty, Semih Yavuz
arXiv:2608. 12564v1 Announce Type: new Abstract: Automating empirical research is a long-standing direction of AI.
By Xiyuan Yang, Sheikh Sarwar, Jingru Cheng, Zhan Shi, Duanshun Li, Huiyuan Chen, Haiyang Zhang, Chenlei Guo, Jingrui He, Zhenyu Liao
MiMo‑V2.6 is an omni‑modal reinforcement learning framework that scales compute to advance large foundation models toward self‑improvement. It trains on a broad multimodal corpus before RL, then scales RL along three axes: larger batches and throughput, diverse environments across code, general, visual, and cyber domains, and enhanced grader compute for better reward signals. The system incorporates infrastructure such as a frozen MoE router, multi‑layer defense against reward hacking, unified trajectory representation, high‑concurrency rollout, and training‑inference consistency, and it is open‑source to support reproducibility and further research.
By Core Team, Zongming Qiao, Ziyue Hua, Zirui Ou, Zihao Yue, Zihan Jiang, Zhuo Huang, Zhiyang Chen, Zhixian Zheng, Zhipeng Xu, Zhengrui Ma, Yuyang Hu, Yuhang Dong, Yuechen Zhang, Yudong Wang, Yuanxin Liu, Yixin Yang, Yishuo Cai, Yikai Zhao, Yihan Yan, Yifan Zhang, Yifan Song, Xiyu Wei, Xing Zhang, Xin Zhang, Xiaoqian Liu, Xiaodong Ji, Xiangwei Deng, Xueyu Guo, Wenhan Ma, Weimin Xiong, Weikun Wang, Weiji Zhuang, Shuo Liu, Shuhuai Ren, Shuhao Gu, Shimao Chen, Shijie Cao, Shihua Yu, Shicheng Li, Shengjie Zhou, Shaolei Zhang, Rang Li, Qiying Wang, Qingkai Fang, Qianli Chen, Minzheng Wang, Liwen Wang, Linli Yao, Linghao Zhang, Liangyu Cheng, Liang Zhao, Lei Li, Jinhao Dong, Jinyu Xiang, Jianyu Wei, Jiangshan Duo, Huaqiu Liu, Huanjie Fan, Hongyi Guan, Hongshen Xu, Hao Tian, Hanyu Li, Hailin Zhang, Gang Wang, Fuli Luo, Feng Wei, Dong Zhang, Dawei Zhu, Chiheng Lou, Chenhong He, Chenhao He, Chenghua Liu, Bowen Ye, Bowen Shen, Boshen Xu, Bo Yang, Bingquan Xia, Bangjun Xiao, Baixuan Xu, Zhouxiang Mao, Zhiyang Zhang, Zhixiang Xu, Zhenru Lin, Zhengju Tang, Zhaojun Huang, Yuzhe Weng, Yuxing Xiang, Yuxiao Li, Yuheng Yang, Yuhang Wang, Yuchen Liu, Yuanyuan Tian, Yuanliang Dong, Yu Cheng, Yongzhe He, Yongshun Liang, Yong Wang, Yiyan Wang, Yitian Gong, Yijie Zhang, Yanshu Xin, Xun Zhang, Xingjian Zhao, Wenyu Yang, Wenshan Huang, Wenhao Li, Tingwei Huang, Tianyu Yu, Tianyang Lu, Taoyu Yang, Sinan Du, Shutong Tian, Shulin Du, Shengfan Wang, Shanchuan Fang, Qihao Zhang, Qibin Yang, Qian Yu, Qian Tu, Pengrong Xie, Peipei Wang, Peidian Li, Minkun Guo, Mingchen Shao, Luohan Gao, Lijie Wang, Liang Shi, Kaiqi Chen, Kaiming Liu, Kaifei Wang, Kai Yang, Jinlong Xue, Jiechen Zhang, Jiaxuan Liu, Hongxu An, Hao Peng, Hanglong L\"u, Guonan Wang, Feiyu Yang, Fanyu Cao, Fangyue Liu, Fan Cui, Cong Wang, Chun Chen, Chenxu Bai, Chengxuan Zhu, Chenghua Wang, Boyi Zeng
arXiv:2607. 05155v1 Announce Type: cross Abstract: Pretraining scaling laws reveal that model capability improves predictably with data and compute.
By Deyao Zhu, Xin Zhou, Shengling Qin, Xuekai Zhu, Hangliang Ding, Shu Zhong, Zixin Wen, Zhonglin Xie, Chenhui Gou, Linxuan Ren, Yueyang Wang, Junfeng Zhong, Rui Liu, Tian Gao, Yangguang Lin, Jingyuan Zhang, Maojia Song, Xuan Qi, Jinhong Wu, Chenyang Zhang, Yinzhu Piao, Ziru Niu, Hongbin Lin, Lingxiang Meng, Peng Tang, Chengyao Tang, Shanyu Wu, Huanyu Zheng, Yu Liu, Liya Zhu, He Wang, Ming Ding, Ziyu Wan, Hao Liu, Sibo Wang, Haotian Zhu, Xintian Zhang, Nan Chai, Yipeng Liu, Panhao Lai, Sihang Yuan, Zixin Su, Ge Zhang, Wangchunshu Zhou, Yantao Du, Wenhao Huang, Guang Shi
arXiv:2607. 07769v1 Announce Type: cross Abstract: Starting from the utilization of deep neural networks to approximate the state-action value function that led to winning one of the most challenging games, to algorithmic advancements that allowed solving problems without even explicitly stating the rules of the challenge at hand, reinforcement learning research has been the center of remarkable scientific progress for the past decade.
By Ezgi Korkmaz
The paper investigates how data should be scaled in agentic reinforcement learning, where data is now a structured design space of tasks, environments, and trajectories. By fitting per‑axis scaling laws across various large language models and RL algorithms, the authors find that environment diversity has the strongest impact, followed by task and trajectory diversity. Using these laws, they price synthesis methods, identify critical synthetic‑to‑real ratios, and formulate a compute‑optimal budget allocation that can improve efficiency by up to 1.7× compared to the common practice of scaling trajectories alone.
By Bowei He, Yankai Chen, Xiaokun Zhang, Changjiang Han, Ye Yuan, Chong Li, Xue Liu
arXiv:2604. 17931v3 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a powerful training paradigm for LLM-based agents.
By Wanli Li, Bince Qu, Bo Pan, Jianyu Zhang, Zheng Liu, Pan Zhang, Wei Chen, Bo Zhang
The paper introduces CLAW, a method that uses a hypernetwork to generate low‑rank adapters for world models during test time, enabling efficient adaptation to new environments with only a few episodes of interaction. By jointly pretraining the hypernetwork and base model on simulated adaptations, CLAW balances computational efficiency and expressivity, outperforming both in‑context learning and gradient‑based adaptation in locomotion and manipulation tasks. The approach also mitigates overfitting in data‑scarce regimes and demonstrates that the benefit stems from expressive adapters rather than context conditioning.
By Fernando Palafox, David Fridovich-Keil
Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong performance, they rely on planning and complex training pipelines, making it unclear which components are essential for scalability.
The paper presents a new scaling law for reward optimization in AI alignment, showing that performance scales as Θ(√min{log(M), K}), where M is the number of preference comparisons used to train a proxy reward model and K is the KL‑divergence budget relative to a reference policy. The authors derive this law using an information‑theoretic model, prove its tightness, and validate it with extensive experiments involving a 70B gold reward model and smaller proxy models (0.6B–4B). The empirical results demonstrate a strong fit (R² 97–99 %) across different model sizes, noise levels, and optimization methods, suggesting that reward optimization behaves like a simple selection task over IID Gaussian variables with noisy feedback.
By Ali Aouad, Aymane El Gadarri, Vivek F. Farias