Publication Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training Yuan Xu, Hejian Sang, Zhengze Zhou, Ran He, Zhipeng Wang, A. Geramifard May 2026 arXiv | May 2026
Publication Agent-BRACE: Decoupling Beliefs from Actions in Long-Horizon Tasks via Verbalized State Uncertainty Joykirat Singh, Zaid Khan, Archiki Prasad, Junyan Chen, Akshay Nambi, Hyunji Lee, Elias Stengel-Eskin, Mohit Bansal May 2026 arXiv | May 2026
Publication From Noise to Diversity: Random Embedding Injection in LLM Reasoning Heeju Kim, Seungpil Lee, J. Yeom, Jaewon Sok, Seonghyeon Park, Jeongjae Park, Taesup Kim, Sundong Kim May 2026 arXiv | May 2026
Publication No One Knows the State of the Art in Geospatial Foundation Models Isaac Corley, Nils Lehmann, Caleb Robinson, Gabriel Tseng, Anthony Fuller, Hamed Alemohammad, Evan Shelhamer, Jennifer Marcus, Hannah Kerner May 2026 arXiv | May 2026
Publication Multi-Rollout On-Policy Distillation via Peer Successes and Failures Weicheng Yu, Xiaomin Li, Yizhou Zhao, Xiaoze Liu, Ruowang Zhang, Haixin Wang, Yinyi Luo, Chenglin Wu, Gaurav Mittal, Matt Fredrikson, Yu Hu May 2026 arXiv | May 2026
Publication Language Modeling with Hyperspherical Flows Justin Deschenaux, Caglar Gulcehre May 2026 arXiv | May 2026
Publication DeepRefine: Agent-Compiled Knowledge Refinement via Reinforcement Learning Haoyu Huang, Jiaxin Bai, Shujie Liu, Yang Wei, Hong Ting Tsang, Yisen Gao, Zhongwei Xie, Yufei Li, Yangqiu Song May 2026 arXiv | May 2026
Publication Sample-Mean Anchored Thompson Sampling for Offline-to-Online Learning with Distribution Shift Bochao Li, Yao Fu, Wei Chen, Fang-yuan Kong May 2026 arXiv | May 2026
Publication Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models Andreas Bergmeister, Stefanie Jegelka, Nikolas Nusken, Carles Domingo-Enrich, Jakiw Pidstrigach May 2026 arXiv | May 2026
Publication EmbodiSkill: Skill-Aware Reflection for Self-Evolving Embodied Agents Ruofei Ju, Xinrui Wang, Xin Ding, Yifan Yang, Haotian Wu, Shiqi Jiang, Qianxi Zhang, Hao Wen, Xiangyu Li, Weijun Wang, Kunchang Li, Yunxin Liu, Haipeng Dai, Wei Wang, Ting Cao May 2026 arXiv | May 2026