标签
This paper proposes PRISM, a multi-reward RL framework that decomposes policy space rather than mixing rewards, improving multi-reward optimization and enabling inference-time controllability. Experiments on reasoning and alignment tasks show it outperforms existing baselines.
本文介绍了 RubricEM，这是一个强化学习框架，它利用量规引导的策略分解和基于反思的元策略进化，为长篇任务训练深度研究智能体。所得到的 RubricEM-8B 模型通过利用阶段感知规划和更密集的语义反馈，在长篇研究基准测试中表现出强劲的性能。