ToolRosella: 将代码仓库翻译为科学智能体的标准化工具
ToolRosella: Translating Code Repositories into Standardized Tools for Scientific Agents
AI总结：
提出ToolRosella框架，通过仓库分析、工具接口构建、执行测试和迭代修复，自动将异构科学代码仓库转化为标准化、可被智能体调用的工具，在122个仓库上达到61.5%的转换成功率，下游任务成功率为84.0%。
摘要：
基于大型语言模型（LLM）的智能体系统越来越多地用于科学任务，但其实际能力受到可调用的手工策划工具范围狭窄的限制。许多科学计算功能已存在于开源代码仓库中，但这些资源难以标准化、操作化并可靠地供智能体使用。本文提出ToolRosella，一个自动将异构科学代码仓库转化为标准化、可被智能体调用的工具的框架。ToolRosella结合了仓库分析、工具接口构建、执行测试和迭代修复，以解决仓库到工具的标准化问题。在涵盖六个领域35个子学科的122个GitHub仓库上，ToolRosella在迭代修复后达到61.5%的仓库转换成功率，速度比人类工程师快4.4倍。生成的1,580个可调用工具支持84.0%的下游任务成功率，并在集成到其他智能体框架时提升性能，特别是在固定策划库存中缺少所需工具的任务上。
英文摘要：
Large Language Model (LLM)-based agent systems are increasingly used for scientific tasks, yet their practical capability remains constrained by the narrow scope of manually curated tools they can invoke. Much scientific computational functionality already exists in open-source code repositories, but these resources remain difficult to standardize, operationalize, and invoke reliably for agent use. Here we present ToolRosella, a framework that automatically transforms heterogeneous scientific code repositories into standardized, agent-invocable tools. ToolRosella combines repository analysis, tool interface construction, execution testing, and iterative repair to address the problem of repository-to-tool standardization. Across 122 GitHub repositories spanning 35 subdisciplines in six domains, ToolRosella reaches a 61.5\% repository conversion success rate after iterative repair, with a 4.4 speedup over human engineers. The resulting 1,580 callable tools support a downstream task success rate of 84.0\% and improve performance when integrated into other agent frameworks, particularly on tasks whose required tools are absent from fixed, curated inventories.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
