动态评分标准让LLM评估器与策略共同进化，破解高质量样本打分瓶颈
arXiv:2607.20083v1 Announce Type: new Abstract: Post-training with evaluator feedback on policy-induced samples serves as a major mechanism for improv…
用自蒸馏技术增强基于评分标准的强化学习，提升训练效果和泛化能力。
arXiv:2607.18082v1 Announce Type: cross Abstract: Rubric-based RL has recently shown promise in improving LLMs on open-ended tasks. A widely recognize…
LLM agent 行为测试新工具，验证做了什么而非说了什么，开源且实用
Article URL: https://github.com/Kareem-Rashed/rubric-eval Comments URL: https://news.ycombinator.com/item?id=48509073 Points: 1 # Comments: 0
LLM自评不再盲目：动态生成与优化评估标准，让AI判断更准确、更灵活。
arXiv:2605.30568v1 Announce Type: new Abstract: LLM-as-a-Judge is a scalable alternative to human evaluation, yet existing rubric-based methods rely o…
提出RUBRIC-ARROW方法，通过交替点对点标准奖励建模优化LLM在非可验证领域的后训练性能
arXiv:2605.29156v1 Announce Type: new Abstract: Pointwise reward modeling offers critical signals for LLM post-training, yet struggles with absolute s…
提出MIRA方法，通过中训练评分锚定实现来源感知数据选择，提升大模型训练质量。
arXiv:2605.30288v1 Announce Type: new Abstract: Mid-training has become an important stage in modern LLM development, using large-scale curated mixtur…