Tool Use, Unified
Read the original on Hugging Face Blog →The Flow has not summarised this story yet — read it at Hugging Face Blog.
The Flow has not summarised this story yet — read it at Hugging Face Blog.
arXiv:2509. 23426v3 Announce Type: replace Abstract: AI scientists are emerging computational systems that serve as collaborative partners in discovery.
arXiv:2607. 14108v1 Announce Type: cross Abstract: This paper introduces tool efficiency, a new quantitative metric to evaluate the rate of useful tool calls in an LLM agent trajectory.
Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they firs...
arXiv:2607. 04686v1 Announce Type: cross Abstract: Tool calling is central to modern language model agents, but aggregate benchmark scores often hide where tool use fails.
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.