科学智能体技能：面向研究智能体的程序知识库
Scientific Agent Skills: A Library of Procedural Knowledge for Research Agents
浏览论文内容
中文总结 AI 辅助
本研究推出含16个领域163种程序的Scientific Agent Skills开放库，为研究智能体提供程序知识，助力生成合理的实验分析。
中文摘要 AI 辅助
当要求语言模型智能体分析一项实验时，它通常会返回可运行的代码，但分析是否合理则是另一回事。合理的分析取决于程序选择：该领域接受哪种检验、哪个标识符命名空间具有权威性，以及结果必须附带哪些警示。我们推出Scientific Agent Skills，这是一个开放库，包含16个实践领域的163种此类程序，涵盖基因组学、化学信息学、医学成像、研究设计和科学传播等。每项技能是围绕带版本号的人类可读指令文件构建的目录，智能体仅在任务需要时加载该文件；该目录通常还包含参考材料和可运行脚本。我们未报告任务级评估结果和宿主选择率，该库采用开放许可，可在此https URL获取。
英文摘要
A language-model agent asked to analyse an experiment will usually return working code. Whether the analysis is defensible is a different question. A defensible analysis depends on procedural choices: which test the field accepts, which identifier namespace is authoritative, and which caveats must accompany a result. We present Scientific Agent Skills, an open library of 163 such procedures in 16 areas of practice, including genomics, cheminformatics, medical imaging, study design and scientific communication. Each skill is a directory built around a versioned, human-readable instruction file. An agent loads the file only when a task calls for it; the directory often also contains reference material and runnable scripts. We report no task-level evaluation and no host selection rate. We measure two properties of the documentation corpus: the always-resident descriptions of all 163 skills cost 7.1% of a 200,000-token window, and the median documented workflow fits within 23.9% of it, although 29 of 46 would overflow if every reference file were loaded. Openly licensed and available at https://github.com/K-Dense-AI/scientific-agent-skills.
发表机构
- K-Dense, Inc.（K-Dense公司）
机构由 AI 辅助整理，请以论文原文为准。
