AI与物理交叉前沿，看如何将实验知识系统整合进计算物理模型，ICML研讨会力作。
arXiv:2603.13191v2 Announce Type: replace-cross Abstract: While large language models (LLMs) have transformed AI agents into proficient executors of c…
不用“本文”开头：这套容错型LLM流水线，从语料直通学术手稿，在计算物理前沿展示了自主研究的完整闭环。
arXiv:2607.02329v1 Announce Type: new Abstract: Autonomous-research agents have demonstrated end-to-end LLM automation in machine-learning sandboxes w…
结合随机最优控制理论，为稀有事件分析提供新视角，交叉领域前沿方法值得关注。
arXiv:2604.13213v2 Announce Type: replace-cross Abstract: Rare events such as conformational changes in biomolecules, phase transitions, and chemical …
被ICML 2026接收，用粗粒度玻尔兹曼生成器加速分子模拟，突破传统采样瓶颈
arXiv:2602.10637v2 Announce Type: replace Abstract: Sampling equilibrium molecular configurations from the Boltzmann distribution is a longstanding ch…