1
Complementary RL: Towards Efficient Experience-Driven Agent Learning
聚焦大模型智能体强化学习效率瓶颈，提出互补RL框架，利用跨回合经验驱动学习，值得关注。
arXiv:2603.17621v2 Announce Type: replace Abstract: Reinforcement Learning (RL) has emerged as a powerful paradigm for training LLM-based agents, yet …