arXiv · NLP· Jianyuan Zhong, Chenwei Wu, Zhaochen Yu, Xixian Jiang, Xuewei Li, Hao Xiao, Xilin Dai, Junyang Wang, Jiaru Zou, Zhiqing Cui, Boyuan Zheng, Jing Xiong, Zhen Zhang, Qiang Gao, Michael Morley, Luis Nakayama, Qiang Xu, Liyue Shen, Tao Gui, Leo Anthony Celi, James Zou, Zhenfei Yin, Yingcheng Wu, Ling Yang·· 5 小时前AI 评分39
DiscoveryRSI：通过递归学习发现高价值假设
DiscoveryRSI: Recursively Learning to Discover Valuable Hypotheses
AI 导读
DiscoveryRSI 框架提出多智能体进化搜索与递归学习机制，用于构建假设树并将研究转化为可执行任务。在 DFM-Bench 评估中，经过两轮自改进后，假设质量评分从基线模型的 4.86 提升至 5.39。
来源：arXiv · NLP · arxiv.org