Paper: Code-First Tool Calling Beats JSON for Agents

eyishazyer · x · 2026-08-15

A perspective suggests JSON tool calling is an unnecessary bottleneck for newer AI agents, and capable models can orchestrate tools better by writing code.

A paper compares standard JSON calls with a code-first setup where the model writes one Python script to invoke the same tools. Across 14 models on a 309-task BFCL v4 subset, programmatic tool calling matched or beat JSON in 11 models.

Related event: Study: Code-First Tool Calling Outperforms JSON(2 posts)→

Original post →

More from coding & agent

coding & agent channel →