English

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

Computation and Language 2024-04-09 v1 Artificial Intelligence

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 compliant datasets at scale for \textbf{personalized agent tuning}. Additionally, \textsc{Mimir} supports the generation of general instruction-tuning datasets from the same input. This dual capability ensures that language agents developed through the platform possess both specific agent abilities and general competencies. \textsc{Mimir} integrates these features into a cohesive end-to-end platform, facilitating everything from the uploading of personalized files to one-click agent fine-tuning.

Keywords

Cite

@article{arxiv.2404.04285,
  title  = {MIMIR: A Streamlined Platform for Personalized Agent Tuning in Domain Expertise},
  author = {Chunyuan Deng and Xiangru Tang and Yilun Zhao and Hanming Wang and Haoran Wang and Wangchunshu Zhou and Arman Cohan and Mark Gerstein},
  journal= {arXiv preprint arXiv:2404.04285},
  year   = {2024}
}
R2 v1 2026-06-28T15:45:25.845Z