Benchmarking Local Language Models for Social Robots using Edge Devices
A survey paper reviews the integration of Large Language Models (LLMs) into Multi-Robot Systems (MRS), categorizing applications from high-level task allocation to low-level action generation. It highlights challenges such as mathematical reasoning limitations and hallucination, while also outlining future research opportunities in fine-tuning and reasoning techniques. Separately, another paper benchmarks 25 open-source language models for deployment on edge devices in social robots, evaluating inference efficiency, general knowledge, and teaching effectiveness. AI
IMPACT Explores LLM integration in robotics for enhanced coordination and efficiency, and benchmarks models for edge deployment in social robots.