CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts 文章

ArXiv CS.AI2026-06-02NEWSen作者: Rui Zhang, Xinle Wu, Yao Lu
查看原文 →
关系图谱

CARE-RL: Capability-Aware Reinforcement Learning for Mitigating Cross-Domain Conflicts · 相关技术

相关技术

Direction-Aware Capability Subspace ProjectionProtocol-Aware Generative Reward ModelCARE-RL