返回首页
arXiv AI··论文与技术

Should SLMs be in the Driver's Seat? A Study of Local Models as Interpreters in Cloud-Written Agent Programs

中文摘要

研究探讨了将云端大模型编写的程序在本地小模型上执行的方案,旨在平衡隐私保护与任务执行性能,但仍面临动态数据交互的挑战。

English Summary

This study explores using cloud models to write programs for local small models, aiming to balance data privacy with task performance while addressing execution limitations in dynamic environments.

原文节选

arXiv:2610.14209v1 Announce Type: new Abstract: The most accurate agents executing user-provided tasks are driven by large, cloud-hosted models, which solve them by reading the private data of the user. Agents powered by models small enough to run on edge devices keep that data local, but yield far worse results. A third option is to have cloud models write a program that devices execute: the data stays local, but as the program is written before any data is seen, it fails whenever a step depends on interpreting content that appears only at run time. We explore an intermediate architecture, in which the cloud-written program defers bounded questions over user data to a small local model through an ordinary function call. On AppWorld this improves the success rate of a code-only agent in all six combinations of backbone model and test partition we evaluate, by up to 14.9pp, recovering a substantial part of the gap to a cloud-hosted ReAct loop while keeping user data on the device.