180k typed tool-calling decisions released so tiny models can route tools

MaziyarPanahi · x · 2026-09-29

Maziyar Panahi is releasing a dataset of 180,000 Jev-format tool-calling decisions, fully typed and labeled across three axes: which tool to call, whether to call one at all, and whether the args are complete. The data is built on NVIDIA's open agent dataset with clean train/val/test splits.

The idea: train your own small router model to make these decisions instead of paying an LLM to do it, then race it against Jev.

Related event: 180K Tool-Calling Decision Dataset Open-Sourced to Train Smaller Router Models(2 posts)→

Original post →

More from coding & agent

coding & agent channel →