Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2506.19998 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913911587995648 |
|---|---|
| author | Ni, Xinyi Jian, Haonan Wang, Qiuyang Shah, Vedanshi Chetan Hong, Pengyu |
| author_facet | Ni, Xinyi Jian, Haonan Wang, Qiuyang Shah, Vedanshi Chetan Hong, Pengyu |
| contents | REST APIs play important roles in enriching the action space of web agents, yet most API-based agents rely on curated and uniform toolsets that do not reflect the complexity of real-world APIs. Building tool-using agents for arbitrary domains remains a major challenge, as it requires reading unstructured API documentation, testing APIs and inferring correct parameters. We propose Doc2Agent, a scalable pipeline to build agents that can call Python-based tools generated from API documentation. Doc2Agent generates executable tools from API documentations and iteratively refines them using a code agent. We evaluate our approach on real-world APIs, WebArena APIs, and research APIs, producing validated tools. We achieved a 55\% relative performance improvement with 90\% lower cost compared to direct API calling on WebArena benchmark. A domain-specific agent built for glycomaterial science further demonstrates the pipeline's adaptability to complex, knowledge-rich tasks. Doc2Agent offers a generalizable solution for building tool agents from unstructured API documentation at scale. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_19998 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Doc2Agent: Scalable Generation of Tool-Using Agents from API Documentation Ni, Xinyi Jian, Haonan Wang, Qiuyang Shah, Vedanshi Chetan Hong, Pengyu Computation and Language REST APIs play important roles in enriching the action space of web agents, yet most API-based agents rely on curated and uniform toolsets that do not reflect the complexity of real-world APIs. Building tool-using agents for arbitrary domains remains a major challenge, as it requires reading unstructured API documentation, testing APIs and inferring correct parameters. We propose Doc2Agent, a scalable pipeline to build agents that can call Python-based tools generated from API documentation. Doc2Agent generates executable tools from API documentations and iteratively refines them using a code agent. We evaluate our approach on real-world APIs, WebArena APIs, and research APIs, producing validated tools. We achieved a 55\% relative performance improvement with 90\% lower cost compared to direct API calling on WebArena benchmark. A domain-specific agent built for glycomaterial science further demonstrates the pipeline's adaptability to complex, knowledge-rich tasks. Doc2Agent offers a generalizable solution for building tool agents from unstructured API documentation at scale. |
| title | Doc2Agent: Scalable Generation of Tool-Using Agents from API Documentation |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2506.19998 |