SOURCE-LINKED INTELLIGENCE

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

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Large language models (LLMs) augmented with external tools have demonstrated remarkable capability in solving complex real-world tasks. However, existing approaches suffer from two key challenges: brittle multi-step and multi-turn reasoning caused by incompatible tool output types and API schemas, and performance degradation under large tool catalogues. To address these, we introduce \textbf{Tool Primitives}, a design that replaces rigid API schema-based invocation with natural language as the interface for tool calling, where each tool is wrapped with an LLM interface that handles schema reso

Read original source ↗ Open in workspace

recordType

paper

region

Global