Hanminwang Hanminwang


2024

pdf bib
MIMIR: A Customizable Agent Tuning Platform for Enhanced Scientific Applications
Xiangru Tang | Chunyuan Deng | Hanminwang Hanminwang | Haoran Wang | Yilun Zhao | Wenqi Shi | Yi Fung | Wangchunshu Zhou | Jiannan Cao | Heng Ji | Arman Cohan | Mark Gerstein
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

Recently, large language models (LLMs) have evolved into interactive agents, proficient in planning, tool use, and task execution across various tasks. However, without agent-tuning, open-source models like LLaMA2 currently struggle to match the efficiency of larger models such as GPT-4 in scientific applications due to a lack of agent tuning datasets. In response, we introduce MIMIR, a streamlined platform that leverages large LLMs to generate agent-tuning data for fine-tuning smaller, specialized models. By employing a role-playing methodology, MIMIR enables larger models to simulate various roles and create interaction data, which can then be used to fine-tune open-source models like LLaMA2. This approach ensures that even smaller models can effectively serve as agents in scientific tasks. Integrating these features into an end-to-end platform, MIMIR facilitates everything from the uploading of scientific data to one-click agent fine-tuning. MIMIR is publicly released and actively maintained at https://github. com/gersteinlab/MIMIR, along with a demo video for quick-start, calling for broader development.