PPL
Dianzhi Yu
Papers (4)
Dynamic Mixture of Latent Memories for Self-Evolving AgentsLC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward DecompositionTowards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system securityReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning