MIMIR: A Streamlined Platform for Personalized Agent Tuning in Domain Expertise
This addresses the need for efficient agent tuning in domain expertise, but it is incremental as it builds on existing fine-tuning methods with a new platform.
The paper tackles the problem of open-source LLMs struggling to match GPT-4 in agent tasks due to a lack of agent-tuning datasets, by introducing MIMIR, a platform that enables personalized agent tuning using private and public datasets, resulting in agents with both specific and general abilities.
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.