RISED：面向智能体多环境选择与自蒸馏的评分标准
原标题：RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation
AI 摘要
Apple 机器学习研究团队提出 RISED 方法，利用跨环境共享的评分标准（rubrics）来指导多环境 LLM 智能体的在线数据选择与策略监督。该方法通过 LLM 评判器为每条 rollout 打上行为标签，据此选择与混合环境批次行为构成一致的数据，并用正向 rubric 作为自蒸馏教师的特权上下文、负向 rubric 引导后续生成避开失败模式。实验显示 RISED 在不同模型骨干上取得最高的平均通过率，并在每个单独环境中排名第一或第二。
正文节选
RISED: Rubrics for Agentic Multi-Environment Selection and Self-Distillation AuthorsJingtan Wang†**, Sirajul Salekin, Young mok Jung, Javier Movellan, Bryan Kian Hsiang Low†, Manjot Bilkhu Training a single LLM agent jointly across diverse interactive environments has attracted increasing attention as a route to generalist agents. Existing curriculum and data-selection strategies often allocate training at the environment level or prioritize local reward-based signals, without explicitly conside