Fanqi Kong

multi-agent system (2) reinforcement learning (2) decision making (1) direct preference optimization (1) preference optimization (1) environment design (1) counterfactual reasoning (1) mixed-motive game (1) multi-agent simulation (1) social bot (1) large language model (1) human-like behavior (1) human-like generation (1) social structure (1) adversarial learning framework (1) adaptive environment (1) adversarial learning (1)