Sibyl: An Efficient Small-large Model Collaboration Framework for Long-horizon Tasks

Excerpt

arXiv:2610.05383v1 Announce Type: new Abstract: Small language models (SLMs) offer a promising foundation for on-device agents through low-latency, resource-efficient inference, yet limited reasoning and planning capabilities constrain their performance on long-horizon tasks requiring multi-step interaction with the environment. Step-level collaboration between SLMs and larger cloud-hosted models can bridge this gap, but identifying states that warrant cloud assistance remains challenging: the c