# Local models improve edge AI agent success rates

> A hybrid cloud‑edge approach raised success by up to 14.9 pp on AppWorld tests, keeping user data on the device.

Oossa · 2026-10-14 · https://oossa.com/en/local-models-improve-edge-ai-agent-success-rates

Researchers led by Boris Radovič explored a middle ground between cloud‑only AI agents and tiny on‑device models. The cloud writes a program, but when it needs to interpret user data it calls a small local model. Tests on the AppWorld benchmark showed the hybrid design lifted the code‑only agent’s success rate in all six model‑partition combos, adding as much as 14.9 percentage points and closing much of the gap to a fully cloud‑hosted ReAct loop while preserving privacy.

## The facts

- Improved success rate by up to 14.9 percentage points
- Evaluated on AppWorld across six backbone‑model and test‑partition combinations

## Why it matters

Edge device users can get more accurate AI assistants without sending their private data to the cloud.

## Sources & references

1. [Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs](https://arxiv.org/abs/2610.14209) – arXiv, 2026-10-14

Last updated: 2026-10-14