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-Example Tool-Calling Dataset Open-Sourced for Small Model Routers(3 posts)→
More from coding & agent
- Generic API-catalog MCP server vs one tool per job: a context-bloat experiment — MandeepKaur9407 · 2026-11-16
- Berkeley paper: LLMs answer with stale values even when the update is in context — ombre-ai · 2026-11-16
- Effective HTML: 4.2k-star agent skills turn wireframes into self-contained interactive prototypes — tom_doerr · 2026-11-16
- skills-gate: one gate skill fronts 148 agent skills at just 389 tokens — Distinct-Pie2389 · 2026-11-16
- Open-weight Karpo-Decision-31B tops Decision Index at 73.9, one forward pass per answer — CodeByPoonam · 2026-11-16
- shadcn boosts @uisdk: one-shot UI rebuild that's instantly E2E-testable by AI — shadcn · 2026-11-16