Magma: A Foundation Model for Multimodal AI Agents
Jianwei Yang, Reuben Tan, Qianhui Wu, Ruijie Zheng, Baolin Peng, Yongyuan Liang, Yu Gu, Mu Cai, Seonghyeon Ye, Joel Jang, Yuquan Deng, Lars Liden, Jianfeng Gao
- 🏛 Institutions
- Microsoft Research, University of Maryland, University of Wisconsin-Madison, KAIST, University of Washington
- 📅 Date
- February 18, 2025
- 📑 Publisher
- CVPR 2025
- 💻 Env
- 🔑 Keywords
TLDR
Magma is a multimodal foundation model for agentic tasks spanning digital and physical environments rather than a GUI-specific paper. It is relevant here because it reports strong UI navigation results and uses Set-of-Mark and Trace-of-Mark supervision, but its main contribution is a broader agentic model covering robotics as well as GUI tasks.
Related papers
- Training Computer Use Agents to Assess the Usability of Graphical User InterfacesApril 28, 2026 · arXiv
- ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI AgentsApril 13, 2026 · arXiv
- MolmoWeb: Open Visual Web Agent and Open Data for the Open WebApril 9, 2026 · arXiv
- IntentScore: Intent-Conditioned Action Evaluation for Computer-Use AgentsApril 6, 2026 · arXiv
- SecAgent: Efficient Mobile GUI Agent with Semantic ContextMarch 9, 2026 · arXiv
- Mobile-Agent-v3.5: Multi-platform Fundamental GUI AgentsFebruary 15, 2026 · arXiv