Research

Paper

AI LLM March 10, 2026

ToolRosetta: Bridging Open-Source Repositories and Large Language Model Agents through Automated Tool Standardization

Authors

Shimin Di, Xujie Yuan, Hanghui Guo, Chaoqian Ouyang, Zhangze Chen, Ling Yue, Libin Zheng, Jia Zhu, Shaowu Pan, Jian Yin, Min-Ling Zhang, Yong Rui

Abstract

Reusing and invoking existing code remains costly and unreliable, as most practical tools are embedded in heterogeneous code repositories and lack standardized, executable interfaces. Although large language models (LLMs) and Model Context Protocol (MCP)-based tool invocation frameworks enable natural language task execution, current approaches rely heavily on manual tool curation and standardization, which fundamentally limits scalability. In this paper, we propose ToolRosetta, a unified framework that automatically translates open-source code repositories and APIs into MCP-compatible tools that can be reliably invoked by LLMs. Given a user task, ToolRosetta autonomously plans toolchains, identifies relevant codebases, and converts them into executable MCP services, enabling end-to-end task completion with minimal human intervention. In addition, ToolRosetta incorporates a security inspection layer to mitigate risks inherent in executing arbitrary code. Extensive experiments across diverse scientific domains demonstrate that ToolRosetta can automatically standardize a large number of open-source tools and reduce the human effort required for code reproduction and deployment. Notably, by seamlessly leveraging specialized open-source tools, ToolRosetta-powered agents consistently improve task completion performance compared to commercial LLMs and existing agent systems.

Metadata

arXiv ID: 2603.09290
Provider: ARXIV
Primary Category: cs.SE
Published: 2026-03-10
Fetched: 2026-03-11 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.09290v1</id>\n    <title>ToolRosetta: Bridging Open-Source Repositories and Large Language Model Agents through Automated Tool Standardization</title>\n    <updated>2026-03-10T07:19:43Z</updated>\n    <link href='https://arxiv.org/abs/2603.09290v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.09290v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Reusing and invoking existing code remains costly and unreliable, as most practical tools are embedded in heterogeneous code repositories and lack standardized, executable interfaces. Although large language models (LLMs) and Model Context Protocol (MCP)-based tool invocation frameworks enable natural language task execution, current approaches rely heavily on manual tool curation and standardization, which fundamentally limits scalability. In this paper, we propose ToolRosetta, a unified framework that automatically translates open-source code repositories and APIs into MCP-compatible tools that can be reliably invoked by LLMs. Given a user task, ToolRosetta autonomously plans toolchains, identifies relevant codebases, and converts them into executable MCP services, enabling end-to-end task completion with minimal human intervention. In addition, ToolRosetta incorporates a security inspection layer to mitigate risks inherent in executing arbitrary code. Extensive experiments across diverse scientific domains demonstrate that ToolRosetta can automatically standardize a large number of open-source tools and reduce the human effort required for code reproduction and deployment. Notably, by seamlessly leveraging specialized open-source tools, ToolRosetta-powered agents consistently improve task completion performance compared to commercial LLMs and existing agent systems.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.SE'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CE'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.MA'/>\n    <published>2026-03-10T07:19:43Z</published>\n    <arxiv:comment>20 pages</arxiv:comment>\n    <arxiv:primary_category term='cs.SE'/>\n    <author>\n      <name>Shimin Di</name>\n    </author>\n    <author>\n      <name>Xujie Yuan</name>\n    </author>\n    <author>\n      <name>Hanghui Guo</name>\n    </author>\n    <author>\n      <name>Chaoqian Ouyang</name>\n    </author>\n    <author>\n      <name>Zhangze Chen</name>\n    </author>\n    <author>\n      <name>Ling Yue</name>\n    </author>\n    <author>\n      <name>Libin Zheng</name>\n    </author>\n    <author>\n      <name>Jia Zhu</name>\n    </author>\n    <author>\n      <name>Shaowu Pan</name>\n    </author>\n    <author>\n      <name>Jian Yin</name>\n    </author>\n    <author>\n      <name>Min-Ling Zhang</name>\n    </author>\n    <author>\n      <name>Yong Rui</name>\n    </author>\n  </entry>"
}