DEVOURED
Qwen Intelligence Launches Three Mobile AI Agents
Qwen Intelligence released three specialized mobile AI agents that achieve a 90% success rate on end-to-end task execution.
What: The agents, focused on planning, cross-app execution, and content creation, are supported by a new suite of open benchmarks including MobilePA-Bench and MobileWorld.
Why it matters: This indicates a shift toward specialized AI agents for mobile environments that require GUI navigation and cross-application coordination rather than just text generation.
Takeaway: Developers can test the new benchmarks and agent code via the official Qwen Intelligence GitHub repositories.
Original article
Introducing Qwen Intelligence, bringing personal intelligence within everyone's reach.
It launches with three SOTA agents:
- Mobile Planner Agent: plans, decomposes & orchestrates complex tasks. #1 on MobilePA-Bench, MobilePA-Bench Business & Memory.
- Mobile-Use Agent: gets things done, API-first with GUI fallback. MobileWorld 82.1, MobileWorld-Real 92.2, AndroidDaily 97.2, 90% end-to-end success rate.
- Mobile Creative Agent: turns one sentence into ready-to-use creations. Image generated in 3s, about 2x faster than leading peers.
We're also opening up our benchmark suite: MobilePA-Bench, MobileWorld, MobileWorld-Real, and MobileWorld-Safety, covering planning, cross-app execution, real-device performance and safety.
Learn more about the agents:
- Qwen Intelligence official website: qwenintelligence.com
- Mobile Planner Agent: github.com/Tongyi-MAI/Qwen-Planner-Agent
- Mobile-Use Agent: tongyi-mai.github.io/Qwen-UI-Agent/
- Mobile Creative Agent: arxiv.org/abs/2608.16887
Explore our open benchmark suite:
- MobilePA-Bench: tongyi-mai.github.io/MobilePA-Bench/
- MobileWorld (GitHub): github.com/Tongyi-MAI/MobileWorld
- Leaderboard: tongyi-mai.github.io/MobileWorld/#leaderboard
Explore all 53 articles in today's digest
Fresh dev news, AI-digested daily. Never miss a trend at devoured.fyi