ToolRosella: Translating Code Repositories into Standardized Tools for Scientific Agents
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909024765607936 |
|---|---|
| author | Di, Shimin Yuan, Xujie Guo, Hanghui Ouyang, Chaoqian Liu, Yongxu Yue, Ling Chen, Zhangze Zheng, Libin Zhu, Jia Pan, Shaowu Yin, Jian Rui, Yong Zhang, Min-Ling |
| author_facet | Di, Shimin Yuan, Xujie Guo, Hanghui Ouyang, Chaoqian Liu, Yongxu Yue, Ling Chen, Zhangze Zheng, Libin Zhu, Jia Pan, Shaowu Yin, Jian Rui, Yong Zhang, Min-Ling |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_09290 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | ToolRosella: Translating Code Repositories into Standardized Tools for Scientific Agents Di, Shimin Yuan, Xujie Guo, Hanghui Ouyang, Chaoqian Liu, Yongxu Yue, Ling Chen, Zhangze Zheng, Libin Zhu, Jia Pan, Shaowu Yin, Jian Rui, Yong Zhang, Min-Ling Software Engineering Computational Engineering, Finance, and Science Multiagent Systems 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. |
| title | ToolRosella: Translating Code Repositories into Standardized Tools for Scientific Agents |
| topic | Software Engineering Computational Engineering, Finance, and Science Multiagent Systems |
| url | https://arxiv.org/abs/2603.09290 |