arXiv cs.LG· Xuying Ning, Dongqi Fu, Tianxin Wei, Yuanchen Bei, Xiyuan Yang, Wujiang Xu, Yueqi Song, Bingxuan Li, Zihao Li, Hanqing Zeng, Xiang Shen, Yajuan Wang, Yifan Wu, Qifan Wang, Jiayi Liu, Hong Li, Yinglong Xia, Xiangjun Fan, Hanghang Tong, Jingrui He·· 5 小时前AI 评分33
EvoHarness-RL：让自进化智能体学会协调运行时 Harness
EvoHarness-RL: Learning Runtime Harness Coordination for Self-Evolving Agents
AI 导读
EvoHarness-RL 是一个将环境相关 harness 实现与共享策略接口分离的统一框架，把外部支持组织为 Belief、Progress、Experience（BPE）工作区，并暴露四个紧凑的 harness 动作。
来源：arXiv cs.LG · arxiv.org