Budget-Constrained Tool Learning with Planning

Yuanhang Zheng, Peng Li, Ming Yan, Ji Zhang, Fei Huang, Yang Liu


Abstract
Despite intensive efforts devoted to tool learning, the problem of budget-constrained tool learning, which focuses on resolving user queries within a specific budget constraint, has been widely overlooked. This paper proposes a novel method for budget-constrained tool learning. Our approach involves creating a preferable plan under the budget constraint before utilizing the tools. This plan outlines the feasible tools and the maximum number of times they can be employed, offering a comprehensive overview of the tool learning process for large language models. This allows them to allocate the budget from a broader perspective. To devise the plan without incurring significant extra costs, we suggest initially estimating the usefulness of the candidate tools based on past experience. Subsequently, we employ dynamic programming to formulate the plan. Experimental results demonstrate that our method can be integrated with various tool learning methods, significantly enhancing their effectiveness under strict budget constraints.
Anthology ID:
2024.findings-acl.536
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
9039–9052
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.536/
DOI:
10.18653/v1/2024.findings-acl.536
Bibkey:
Cite (ACL):
Yuanhang Zheng, Peng Li, Ming Yan, Ji Zhang, Fei Huang, and Yang Liu. 2024. Budget-Constrained Tool Learning with Planning. In Findings of the Association for Computational Linguistics: ACL 2024, pages 9039–9052, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Budget-Constrained Tool Learning with Planning (Zheng et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.536.pdf