Shuyue Hu

large language model (7) multi-agent system (6) game theory (3) model selection (2) repeated sampling (2) model routing (2) reinforcement learning (2) multi-agent q-learning (2) evolutionary dynamics (2) fokker-planck equation (2) model merging (1) multi-agent learning (1) stochastic process (1) ensemble method (1) exploration exploitation (1) in-context learning (1) incomplete information (1) semantic clustering (1) regret minimization (1) model ensemble (1)