MIMIR: A Streamlined Platform for Personalized Agent Tuning in Domain Expertise

arXiv:2404.04285v1 Announce Type: new
Abstract: Recently, large language models (LLMs) have evolved into interactive agents, proficient in planning, tool use, and task execution across a wide variety of tasks. However, without specific agent tuning, open-source models like LLaMA currently struggle to match the efficiency of GPT- 4, particularly given the scarcity of agent-tuning datasets for fine-tuning. In response, we introduce \textsc{Mimir}: a streamlined platform offering a customizable pipeline that enables users to leverage both private knowledge and publicly available, legally …

abstract agent agents arxiv cs.ai cs.cl domain efficiency expertise gpt however interactive language language models large language large language models llama llms match open-source models personalized planning platform struggle tasks tool type