PPL
Yibo Zhao
Papers (6)
Skill0.5: Joint Skill Internalization and Utilization for Out-of-Distribution Generalization in Agentic Reinforcement LearningBeyond Chunk-Local Extraction: Cross-Chunk Graph Augmentation for GraphRAGRetrieval, Reward, and Training Protocols: What Matters in Training Search Agents?MERIT: Matching Expertise via Rubric-Informed Training for Reviewer AssignmentContinuous Discovery of Vulnerabilities in LLM Serving Systems with FuzzingEnabling Performant and Flexible Model-Internal Observability for LLM Inference