← all releases
Alibaba (MAI Team)·Sep 24, 2026·v27B·open source
Qwen-Planner-Agent
Qwen-Planner-Agent is a closed-loop AI-for-AI framework designed for real-world mobile planner agents. It integrates a trained planner model with a stateful harness to manage complex mobile tasks, utilizing persistent memory, reusable skills, and sub-agent coordination to achieve high performance in tool-use and reasoning.
AI AgentsMobile AutomationLLMQwen
overview
Qwen-Planner-Agent is a closed-loop AI-for-AI framework designed for real-world mobile planner agents. It integrates a trained planner model with a stateful harness to manage complex mobile tasks, utilizing persistent memory, reusable skills, and sub-agent coordination to achieve high performance in tool-use and reasoning.
key features
- 01Closed-loop AI-for-AI development lifecycle
- 02Competence-adaptive planner training (CARE)
- 03Contextual memory and state tracking for multi-turn tasks
- 04Coordinated execution and automated error recovery
- 05High performance on MobilePA-Bench with optimized output costs
related productsbrowse all →
MiroThinkeropen sourceMiroThinker is an open-source search agent model developed by MiroMindAI, designed for tool-augmented reasoning and real-world information seeking. It aims to match the deep research capabilities of leading AI models like OpenAI's Deep Research and Google's Gemini Deep Research.Letta Code SDKopen sourceThe Letta Code SDK is a software development kit that enables developers to build deeply personalized agents with persistent memory that learn over time. It serves as the interface to Letta Code, facilitating the creation of stateful agents capable of continuous learning and improvement.OB-1open sourceOB-1 is a self-improving coding agent developed by OpenBlock Labs, designed to autonomously handle the full development lifecycle, from project management to pull requests. It integrates seamlessly into existing workflows, enhancing productivity and code quality.