ToolSmith: A Multi-Agent Framework for Enterprise Tool Creation
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (48) · 41706-41708
DOI: 10.1609/aaai.v40i48.42388 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Purna Chandra Sekhar Vakudavathu und 4 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).
Abstract (Originalsprache)
Although LLMs can generate tools for generic domains and tasks, they struggle with enterprise-related domains that involve proprietary APIs and data schemas. We present ToolSmith, a framework for autonomously generating and validating agent-compatible tools. Given an API specification and a Tool Specification Requirement (TSR), ToolSmith produces a tool function and verifies it through a closed-loop process: it creates natural language (NL) tests and executes the tool in a secure agent sandbox for validation. For state-changing tools, ToolSmith confirms outcomes by querying the API with parameters derived from the NL tests. If the tool fails to produce the desired output, ToolSmith generates diagnostic feedback to iteratively regenerate it. By ensuring both functional correctness and agent compatibility, ToolSmith enables reliable automation of enterprise workflows.
Zitieren
APA
Vakudavathu, P. C. S., Mukherjee, K., Bandlamudi, J., Sindhgatta, R., & Mehta, S. (2026). ToolSmith: A Multi-Agent Framework for Enterprise Tool Creation. Proceedings of the AAAI Conference on Artificial Intelligence, 40(48), 41706-41708. https://doi.org/10.1609/aaai.v40i48.42388
Vancouver
Vakudavathu PCS, Mukherjee K, Bandlamudi J, Sindhgatta R, Mehta S. ToolSmith: A Multi-Agent Framework for Enterprise Tool Creation. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(48):41706-41708. doi:10.1609/aaai.v40i48.42388
BibTeX
@article{Vakudavathu2026,
author = {Vakudavathu, Purna Chandra Sekhar and Mukherjee, Kushal and Bandlamudi, Jayachandu and Sindhgatta, Renuka and Mehta, Sameep},
title = {ToolSmith: A Multi-Agent Framework for Enterprise Tool Creation},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {48},
pages = {41706--41708},
doi = {10.1609/aaai.v40i48.42388}
}
EUVIMED