automodel:把模型发现方法封装成 Agent Skill 的新尝试
automodel: A Skill for Agentic Model Discovery
arXiv 上的一项研究,把模型发现流程写成 Claude Code 和 OpenAI Codex 能直接用的 Skill,在天体物理、交通流等五个领域跑出了可用模型。做科学计算或自动建模的工程师可以直接去 GitHub 拿来试,不用自己搭专用流水线。
一篇来自 arXiv 的论文提出了 automodel,一个面向通用模型发现的 Agent Skill(技能包)。作者的核心问题是:给 Claude Code、OpenAI Codex 这类通用编程智能体配上一份“模型发现配方”,能否让它们自主发现或改进科学模型?
automodel 把模型发现的方法论编码成可移植的技能文件,智能体据此在数据上自动搜索解析方程或神经架构。论文在五个领域做了案例验证:天体物理学、心血管动力学、精准农业、交通流和车辆轮胎动力学,结果显示配备 automodel 的商用智能体能找到新颖且具有科学意义的模型。
作者认为,相比 AlphaEvolve 到穷举搜索这些领域专用自动发现流水线,把方法论做成通用 Skill 是一种更简单、可交互、适用面广的替代路线。技能已开源在 GitHub 的 unlayer-ai/automodel 仓库。
automodel: A Skill for Agentic Model Discovery
The search for better models, whether expressed as analytical equations or neural architectures, has increasingly shifted from manual design toward data-driven automation. While a multitude of algorithms exist, ranging from exhaustive search to AlphaEvolve, recent advances in general-purpose coding agents such as Claude Code and OpenAI Codex raise the question: could providing such systems with a "model discovery recipe" be enough to discover or improve models? We present automodel, an agent skill for general model discovery. With case studies in astrophysics, cardiovascular dynamics, precision agriculture, traffic flow, and vehicle tire dynamics, we show how commercial agents equipped with automodel can successfully identify novel and scientifically-relevant models. Our findings suggest that encoding model-discovery methodology as a portable agent skill can provide a simple, interactive, powerful and broadly applicable alternative to domain-specific automated discovery pipelines. The skill is available at: https://github.com/unlayer-ai/automodel.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:automodel、Claude Code、OpenAI Codex、智能体,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始信息发布自一手权威信源「arXiv: OpenAI」(Tier-1 一手发布),具备高确定性参考价值。