【论文速递】2025年第43周(Oct-19-25)(Robotics/Embodied AI/LLM)中文使用 googletrans 翻译，翻译不对的地方以英文为准Test-time scaling seeks to improve the reasoning performance of large language models (LLMs) by adding computational resources. A prevalent approach within the field is sampling-based test-time scaling methods, which enhanc