Towards Computer-Using Personal Agents
Piero A. Bonatti, John Domingue, Anna Lisa Gentile, Andreas Harth, Olaf Hartig, Aidan Hogan, Katja Hose, Ernesto Jimenez-Ruiz, Deborah L. McGuinness, Chang Sun, Ruben Verborgh, Jesse Wright
TL;DR
Problem: Computer-Using Agents enable automation but risk mishandling sensitive personal data. Approach: introduce Computer-Using Personal Agents (CUPAs) built on a Personal Knowledge Graph (PKG) to regulate access and enable richer, context-aware automation. Contributions: a conceptual framework, capabilities, governance via policy mechanisms like ODRL, and a three-stage roadmap toward API-based interactions and inter-CUPA collaboration. Significance: provides a principled path toward privacy-preserving, autonomous personal assistants capable of coordinating across users and services.
Abstract
Computer-Using Agents (CUA) enable users to automate increasingly-complex tasks using graphical interfaces such as browsers. As many potential tasks require personal data, we propose Computer-Using Personal Agents (CUPAs) that have access to an external repository of the user's personal data. Compared with CUAs, CUPAs offer users better control of their personal data, the potential to automate more tasks involving personal data, better interoperability with external sources of data, and better capabilities to coordinate with other CUPAs in order to solve collaborative tasks involving the personal data of multiple users.