Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,26 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
-
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
---
|
| 4 |
+
# MAI-UI: Real-World Centric Foundation GUI Agents.
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
## 📖 Background
|
| 8 |
+
The development of GUI agents could revolutionize the next generation of human-computer interaction. Motivated by this vision, we present MAI-UI, a family of foundation GUI agents spanning the full spectrum of sizes, including 2B, 8B, 32B, and 235B-A22B variants. We identify four key challenges to realistic deployment: the lack of native agent–user interaction, the limits of UI-only operation, the absence of a practical deployment architecture, and brittleness in dynamic environments. MAI-UI addresses these issues with a unified methodology: a self-evolving data pipeline that expands the navigation data to include user interaction and MCP tool calls, a native device–cloud collaboration system that routes execution by task state, and an online RL framework with advanced optimizations to scale parallel environments and context length.
|
| 9 |
+
|
| 10 |
+
## 🏆 Results
|
| 11 |
+
|
| 12 |
+
MAI-UI establishes new state-of-the-art across GUI grounding and mobile navigation.
|
| 13 |
+
|
| 14 |
+
- On grounding benchmarks, it reaches 73.5% on ScreenSpot-Pro, 91.3% on MMBench GUI L2, 70.9% on OSWorld-G, and 49.2% on UI-Vision, surpassing Gemini-3-Pro and Seed1.8 on ScreenSpot-Pro.
|
| 15 |
+
|
| 16 |
+
|
| 17 |
+
|
| 18 |
+
|
| 19 |
+
|
| 20 |
+
- On mobile GUI navigation, it sets a new SOTA of 76.7% on AndroidWorld, surpassing UI-Tars-2, Gemini-2.5-Pro and Seed1.8. On MobileWorld, MAI-UI obtains 41.7% success rate, significantly outperforming end-to-end GUI models and competitive with Gemini-3-Pro based agentic frameworks.
|
| 21 |
+
|
| 22 |
+
|
| 23 |
+
|
| 24 |
+
- Our online RL experiments show significant gains from scaling parallel environments from 32 to 512 (+5.2 points) and increasing environment step budget from 15 to 50 (+4.3 points).
|
| 25 |
+
|
| 26 |
+
|