MMODELYST
People/Zhezheng Hao
PPL

Zhezheng Hao

Papers (3)
Meta-Cognitive Memory Policy Optimization for Long-Horizon LLM AgentsEvolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent SystemsPDEAgent-Bench: A Multi-Metric, Multi-Library Benchmark for PDE Solver Generation