多智能体强化学习突破：在赛车场景中实现超人类安全与敏捷，解决单智能体在共享动态空间中的脆弱性
arXiv:2605.22748v1 Announce Type: cross Abstract: Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain …
ICML 2026最新研究：利用大语言模型引导多智能体间的通信策略，提升合作强化学习效率。
arXiv:2605.18077v1 Announce Type: cross Abstract: Communication is a key component in multi-agent reinforcement learning (MARL) for mitigating partial…
融合LLM与多智能体强化学习，打造弹性的云网络防御框架，有效应对虚拟化带来的安全挑战。
arXiv:2601.07122v2 Announce Type: replace-cross Abstract: While virtualization and resource pooling empower cloud networks with structural flexibility…