Hugging Face Blog

Tool Use, Unified

arXiv Computation and Language
Nov 5

Growing One's AI Tools: A Paradigm of Practice-Grown Tools

The article describes how a conference interpreter, without programming training, built and iteratively improved a computer-assisted interpreting (CAI) tool over eight weeks, using version control and telemetry from 133 sessions and 20,000 utterances. The tool evolved through 62 commits and six versions, with a strategy change that reduced median end‑to‑end delay by more than a third within a single afternoon. The authors introduce the paradigm of practice‑grown tools, outlining its defining characteristics and proposing three propositions for assessing practitioners and their tools together.

By Zeming Zhao
arXiv AI
Sep 3

Harness Engineering in LLM Tool Use via Agent-Native Reusable Tool Primitives

The paper introduces Tool Primitives, a design that replaces rigid API schemas with natural language interfaces for tool calling, enabling seamless inter-tool communication. It builds ToolFace, a repository of over 25,000 functions that LLMs can dynamically retrieve, and HEART, a harness engineering framework that orchestrates tool use with planning, routing, and verification. Experiments show HEART outperforms fine‑tuned models and leading commercial LLMs while cutting API costs by up to 85%.

By Haibo Jin, Suijin Wang, Xucheng Yu, Haojing Luo, Haohan Wang
arXiv AI
Oct 16

Rethinking the Role of Tool Graph Memory in Multi-Turn Tool Use

The paper investigates the effectiveness of tool graph memory—a component that records past tool transitions to guide future tool selection—in large language model agents performing multi‑turn tasks. Across nine models and two benchmarks, the authors find that tool graph memory rarely yields significant performance gains, often incurs more than twice the number of LLM calls, and its guidance is frequently incorrect. They observe that random or no guidance can achieve similar improvements, suggesting the benefits arise from additional computation rather than the memory itself, and that storing experiences as textual insights outperforms the graph approach with minimal extra calls.

By Uiji Hwang, Richeng Xuan, Taeuk Kim