Xihuai Wang

multi-agent system (2) multi-agent reinforcement learning (2) sample efficiency (1) policy optimization (1) code generation (1) llm evaluation (1) out-of-distribution generalization (1) model-based reinforcement learning (1) human-ai collaboration (1) zero-shot coordination (1) evaluation benchmark (1) cooperative multi-agent (1) behavior diversity (1) opponent modeling (1) multi-turn dialogue (1) multi-agent debate (1) theory of mind (1) contrastive analysis (1) language agent (1) function calling (1)