PPL
Wenhao Li
Papers (5)
Unifying Temporal and Structural Credit Assignment in LLM-Based Multi-Agent Prompt OptimizationMean-Field Diffuser: Scaling Offline MARL to Thousands of AgentsAgentSchool: An LLM-Powered Multi-Agent Simulation for EducationBlocked Gibbs meets Diffusion Transformers: Unsupervised Learning for Constraint OptimizationThe Reciprocity Gradient