A Paper Suggests JSON Tool Calling Is a Bottleneck — Code-First Wins in 11 Models

New research finds that letting models call tools programmatically, rather than through structured JSON, matches or beats the standard approach on complex multi-tool tasks.

One of the load-bearing conventions of agent architecture may be quietly wrong. A new arXiv paper, surfaced by @rohanpaul_ai, argues that "JSON tool calling may be an unnecessary bottleneck." The study compares the standard JSON-based approach — where a model emits structured arguments for each tool call — against a code-first setup in which the model writes actual code to orchestrate tools. Programmatic tool calling matched or beat JSON across 11 models.

Lorem ipsum dolor sit amet, consectetur adipiscing elit. Sed do eiusmod tempor incididunt ut labore et dolore magna aliqua. Ut enim ad minim veniam, quis nostrud exercitation ullamco laboris nisi ut aliquip ex ea commodo consequat. Duis aute irure dolor in reprehenderit in voluptate velit esse cillum dolore eu fugiat nulla pariatur. Excepteur sint occaecat cupidatat non proident, sunt in culpa qui officia deserunt mollit anim id est laborum. Vestibulum ante ipsum primis in faucibus orci luctus et ultrices posuere cubilia curae.

Pellentesque habitant morbi tristique senectus et netus et malesuada fames ac turpis egestas. Proin pharetra nonummy pede. Mauris et orci. Aenean nec lorem. In porttitor. Donec laoreet nonummy augue. Suspendisse dui purus, scelerisque at, vulputate vitae, pretium mattis, nunc. Mauris eget neque at sem venenatis eleifend. Ut nonummy. Fusce aliquet pede non pede. Suspendisse dapibus lorem pellentesque magna integer malesuada.

Unlock the full briefing

Get every story in today's briefing, the full archive, and the daily AI intelligence brief.

All stories today

Full archive

Daily brief