arXiv · NLP· Yue Huang, Yanbo Wang, Lichi Li, Yuanyuan Chen, Andreas Haupt, Xiaonan Luo, Zheyuan Liu, Jihye Choi, Felix Juefei-Xu, Xiangliang Zhang, Radha Poovendran, Misha Sra, Ying Liu, Ben Burtenshaw, Thomas Wolf, Alex Pentland, Zichen Chen, Zhangchen Xu·· 4 小时前AI 评分57
RSI Arena：探索基于人类反馈的递归自我改进
RSI Arena: Towards Recursive Self-Improvement with Human Feedback
AI 导读
RSI Arena 开展了自主后训练的两阶段研究，10 个前沿模型作为训练代理基于 NVIDIA Nemotron 3.5 Lightning 30B-A3B 独立选择数据与训练过程。
来源：arXiv · NLP · arxiv.org