撰文丨王聪 编辑丨王多鱼 排版丨水成文 " AI for Science "的目标之一，是发现能够通过真实世界实验验证的定制材料。目前，我们在计算预测和材料合成自动化方面已经取得了开创性的进展。然而， 大多数材料实验仍局限于采用单模态主动学习 的 方法，依赖单一的数据流，这限制了 对材料设计和性能优化中固有的复杂性进行深入解析的能力。而 人工智能 （AI） 在解释 实验复杂性中的潜力，在很大程度上仍未得到开发。 2025 年 9 月 23 日，麻省理工学院 （MIT） 李巨 教授团队在国际顶尖学术期刊 Nature 上发表了 题为： A multimodal robotic platform for multi-element electrocatalyst discovery 的研究论文。 该研究推出了一个 多模态 AI 机器人平台 —— CRESt （ Copilot for Real-world Experimental Scientists，真实世界实验科学家副驾驶 ） 。该平台将 大型多 模态模型 （LMM，融合了化学成分、文本嵌入和微观结构图像） 与 知识辅助贝叶斯优化 （KABO） 以及 机器人 ...

Core Viewpoint - A new type of injectable nanobody derived from llama antibodies has been developed, offering a potential new treatment avenue for schizophrenia with fewer side effects [1] Summary by Sections Research Findings - The new nanobody specifically activates glutamate receptors, which are key receptors in the brain associated with schizophrenia, potentially improving cognitive impairments that current treatments do not adequately address [1] - The efficacy of the nanobody has been validated in two animal models, showing significant improvement in cognitive abilities of mice with cognitive impairments, with effects lasting over a week post-injection [1] Administration and Safety - The nanobody can be administered via peripheral injection methods such as intravenous or intramuscular routes, and it is biodegradable with minimal side effects [1] Future Directions - Clinical studies are needed to confirm the effectiveness of this treatment approach, and similar therapies may be applicable to other neurological disorders [1]