PPL
Hong Wang
Papers (4)
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM AgentsEvolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent SystemsArborKV: Structure-Aware KV Cache Management for Scaling Tree-based LLM ReasoningAOT-POT: Adaptive Operator Transformation for Large-Scale PDE Pre-training