AI RESEARCH
Benchmarking Local Language Models for Social Robots using Edge Devices
arXiv CS.CL
•
ArXi:2605.03111v1 Announce Type: cross Social-educational robots designed for socially interactive pedagogical, such as the Robot Study Companion (RSC), rely on responsive, privacy-preserving interaction despite severely limited compute. However, there is a gap in systematic benchmarking of language models for edge computing in pedagogical applications. This paper benchmarks 25 open-source language models for local deployment on edge hardware.