PPL
Xiaoyuan Li
Papers (5)
ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement LearningUnified Data Selection for LLM ReasoningSkillGraph: Skill-Augmented Reinforcement Learning for Agents via Evolving Skill GraphsSAGE: Scalable Automated Robustness Augmentation for LLM Knowledge EvaluationOn Predicting the Post-training Potential of Pre-trained LLMs