材料科学家和 AI for Science 研究者终于有了一个能自动设计描述符的框架——Automat 用 GPT 智能体替代了繁琐的手动特征工程，在带隙和居里温度预测上直接超越经典 Magpie 基线，做材料信息学的团队值得一试。
Autoresearch 是一种自动化科学任务的范式，AI 智能体自主提出、实现、评估和优化解决方案。本文提出 Automat 框架，使用基于 GPT-5.5 的 Codex 编码智能体，为化学化合物生成仅基于化学式的成分描述符，并通过随机森林工作流评估。在预测无机材料带隙和铁磁化合物居里温度两个任务中，Automat 超越了分数成分、Magpie 等基线，生成的描述符具有化学可解释性。该研究证明 autoresearch 智能体无需手动特征工程即可生成任务专用描述符，但也暴露了描述符冗余、贪婪特征扩展敏感性和需要复杂度控制等局限性。
Agentic Design of Compositional Descriptors via Autoresearch for Materials Science Applications
Autoresearch offers a flexible paradigm for automating scientific tasks, in which an AI agent proposes, implements, evaluates, and refines candidate solutions against a quantitative objective. Here, we use composition-based materials-property prediction to test whether such agents can perform a task beyond model selection and hyperparameter optimization: the design of input descriptors. We introduce Automat, an autoresearch framework where a coding agent based on a large language model generates composition-only descriptors for chemical compounds and evaluates them using a random forest workflow. The agent is restricted to information derivable from chemical formulas and iteratively proposes, implements, and tests chemically motivated descriptor strategies. We apply Automat, with OpenAI Codex using GPT-5.5 as the coding agent, to the prediction of experimental band gaps in inorganic materials and Curie temperatures in ferromagnetic compounds. In both tasks, Automat improves over fractional-composition, Magpie, and combined fractional-composition/Magpie baselines, while producing descriptor families that are chemically interpretable. These results provide a demonstration that autoresearch agents can generate competitive, task-specific materials descriptors without manual feature engineering during the run. They also reveal current limitations, including descriptor redundancy, sensitivity to greedy feature expansion, and the need for explicit complexity control, descriptor pruning, and more sophisticated search strategies.