[R] OS-Copilot: Towards Generalist Computer Agents with Self-Improvement - Shanghai AI Laboratory 2024

Paper: https://arxiv.org/abs/2402.07456

Github: https://github.com/OS-Copilot/FRIDAY

Abstract:

Autonomous interaction with the computer has been a longstanding challenge with great potential, and the recent proliferation of large language models (LLMs) has markedly accelerated progress in building digital agents. However, most of these agents are designed to interact with a narrow domain, such as a specific software or website. This narrow focus constrains their applicability for general computer tasks. To this end, we introduce OS-Copilot, a framework to build generalist agents capable of interfacing with comprehensive elements in an operating system (OS), including the web, code terminals, files, multimedia, and various third-party applications. We use OS-Copilot to create FRIDAY, a self-improving embodied agent for automating general computer tasks. On GAIA, a general AI assistants benchmark, FRIDAY outperforms previous methods by 35%, showcasing strong generalization to unseen applications via accumulated skills from previous tasks. We also present numerical and quantitative evidence that FRIDAY learns to control and self-improve on Excel and Powerpoint with minimal supervision. Our OS-Copilot framework and empirical findings provide infrastructure and insights for future research toward more capable and general-purpose computer agents.

https://preview.redd.it/uzec8udohdic1.jpg?width=1655&format=pjpg&auto=webp&s=893b5561ca47c26c789b69925efdc26e5b783007

https://preview.redd.it/vfwfwudohdic1.jpg?width=1653&format=pjpg&auto=webp&s=9eafc2a5ea0ad188a156d3de446508d82d9cc913

https://preview.redd.it/lmi8rwdohdic1.jpg?width=1123&format=pjpg&auto=webp&s=dbc67b27585b980d0c592f9bd9f87f3ec6531f66

https://preview.redd.it/20yo21eohdic1.jpg?width=1037&format=pjpg&auto=webp&s=72fab36d585b862eed4ff6c7deed2be0cd62f637