University of Science and Technology of China
| Name | Categories | Topics | References | Credibility | CreateDate | UpdateDate | Title | RelatedNotes | NavigationOrder | Created |
|---|---|---|---|---|---|---|---|---|---|---|
| 20260707_evopolicygym_evaluating_autonomous_policy_evolution | paper_analysis | embodied_ai, reinforce_learning, self_evolving_agents, evaluation, agent_architecture | cuhk_shenzhen, sjtu, tsinghua_university, ustc | 100 | EvoPolicyGym: Evaluating Autonomous Policy Evolution in Interactive Environments | demopsd_disagreement_modulated_policy_self_distillation, llm_agents_social_structure_latent_objective_emergence, recontext_recursive_evidence_replay, evolvenav_proactive_preflection_self_evolving_memory | [object Object] |