File:Overview of TaskMatrix.AI (for enabling completing tasks by connecting foundation models with many APIs).jpg
Summary
| Description |
English: "Given user instructions and the conversational context, the MCFM first generates a solution outline (step 1), which is a textual description of the steps needed to perform the task. Then, the API selector chooses the most relevant APIs from the API platform according to the solution outline (step 2). Next, the MCFM generates action code using the recommended APIs. The code is executed by calling APIs. Finally, the user’s feedback on task completion is returned to the MCFM and the API developers." |
| Date | |
| Source | https://spj.science.org/doi/10.34133/icomputing.0063 |
| Author | Authors of the study: Yaobo Liang https://orcid.org/0000-0002-6595-5145, Chenfei Wu, Ting Song, Wenshan Wu, Yan Xia, Yu Liu, Yang Ou, Shuai Lu, Lei Ji, Shaoguang Mao, Yun Wang, Linjun Shou, Ming Gong, and Nan Duan |
Licensing
This file is licensed under the Creative Commons Attribution 4.0 International license.
- You are free:
- to share – to copy, distribute and transmit the work
- to remix – to adapt the work
- Under the following conditions:
- attribution – You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
.jpg){kind=link}