English

Budget-Constrained Tool Learning with Planning

Artificial Intelligence 2024-06-12 v2

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.

Keywords

Cite

@article{arxiv.2402.15960,
  title  = {Budget-Constrained Tool Learning with Planning},
  author = {Yuanhang Zheng and Peng Li and Ming Yan and Ji Zhang and Fei Huang and Yang Liu},
  journal= {arXiv preprint arXiv:2402.15960},
  year   = {2024}
}

Comments

Accepted for Findings of ACL 2024

R2 v1 2026-06-28T14:59:17.811Z