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)→
More from coding & agent
- Devs say LLM coding mistakes are a different class: overcomplication, inferred limits, worse at higher reasoning — Mu5_ · 2026-10-16
- How do you debug bad agent runs when you already have tracing? — Sensitive-Parsnip-12 · 2026-10-16
- Where does pre-task context live for agents? Devs debate workflows beyond handoff — shishen2026 · 2026-10-16
- No-instruction autonomous agent wakes up, sets own goals, and tries hacking by default — sethlazar · 2026-10-16
- CODESTRUCT reframes codebases as AST action spaces to fix brittle LLM code agents — burkov · 2026-10-16
- Would you install another SDK for agent debugging on top of your tracing stack? — Sensitive-Parsnip-12 · 2026-10-16