Preprint
Jul 2026
MORES: Mobile Reasoning-as-a-Service via Distributed LLM Inference-Time Scaling
A Mobile Reasoning-as-aService (MORES) framework that treats reasoning as a computational service accessible to edge devices over wireless networks, and focuses on implicit reasoning, which achieves an approximately 18% improvement in system throughput over the baseline Soft Actor-Critic (SAC) algorithm.
Guanchen Liu, Hongyang Du, Kaibin Huang
· 1 citation