引用本概念的论文(2)
- 超越静态评估:为可扩展的智能体强化学习构建仿真环境 Beyond Static Evaluation: Building Simulation Environments for Scalable Agentic Reinforcement Learning arXiv 2607.05773
- 关于偏好对齐生成中引导向量局限性的研究 On the Limits of Steering Vectors for Preference-Aligned Generation arXiv 2607.01802