local-cloud-collaboration

Tag

Cards List
#local-cloud-collaboration

Routing Without Training: Controllable-Ratio LLM Offloading via Reliability Gating

arXiv cs.AI · 15h ago Cached

This paper introduces CARGO, a training-free routing framework that uses the local LLM's own inference-time agreement across sampled responses to decide when to offload to a cloud model, enabling controllable collaboration ratios without additional training.

0 favorites 0 likes
← Back to home

Submit Feedback