PPL
Zhengxi Lu
Papers (4)
GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar ReselectionMaestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill EnsemblesSelf-Distilled Agentic Reinforcement LearningSkill1: Unified Evolution of Skill-Augmented Agents via Reinforcement Learning