Magentic-UI: Towards Human-in-the-loop Agentic Systems
Microsoft Research AI Frontiers (MSR), 2025
Magentic-UI is an open-source interface and architecture for studying collaborative workflows between humans and AI agents. The system supports co-planning, action approval, real-time oversight, and memory sharing across long-running web tasks. We argue that human-in-the-loop designs remain essential for deploying powerful agentic systems safely, and we showcase how Magentic-UI enables nuanced oversight and intervention across complex, multi-step scenarios.
@article{mozannar2025magentic,
title={Magentic-UI: Towards Human-in-the-loop Agentic Systems},
author={Mozannar, Hussein and Bansal, Gagan and Tan, Cheng and Fourney, Adam and Dibia, Victor and Chen, Jingya and Gerrits, Jack and Payne, Tyler and Maldaner, Matheus Kunzler and Grunde-McLaughlin, Madeleine and Zhu, Eric and Bassman, Griffin and Alber, Jacob and Chang, Peter and Loynd, Ricky and Niedtner, Friederike and Kamar, Ece and Murad, Maya and Hosn, Rafah and Amershi, Saleema},
journal={arXiv preprint arXiv:2507.22358},
year={2025}
}