Dexun Li

reinforcement learning (3) unsupervised environment design (2) zero-shot learning (1) curriculum learning (1) information retrieval (1) document retrieval (1) out-of-distribution generalization (1) tool use (1) regret minimization (1) constraint satisfaction (1) influence maximization (1) multimodal retrieval (1) social network (1) environment design (1) language model agent (1) llm evaluation (1) task planning (1) retrieval-augmented generation (1) multi-turn dialogue (1) sample efficiency (1)