智能体
arxiv.org ·
Qwen-Planner-Agent：面向真实世界移动规划智能体的闭环 AI-for-AI 框架
该 arXiv 论文提出 Qwen-Planner-Agent，一个闭环 AI-for-AI 框架，用于可扩展地开发与迭代移动规划智能体。框架通过共享的“动作-反馈-验证”契约连接数据生产、模型训练与部署：AI for Data 构建带人工把关的智能体数据飞轮；AI for Training 结合监督式规划冷启动与混合环境在线智能体强化学习，并提出 Competence-Aware Reward-and-Advantage Engineering（CARE）以降低推理与工具调用成本；AI 驱动模型与执行框架协同演化，在运行时编排记忆、技能与工具，并将结构化动作反馈与失败轨迹回传用于联合适配。作者称该模型在自建 MobilePA-Bench 上取得所评估模型与系统中的最佳整体表现，并在工具使用、记忆、技能与子智能体协调上优于基座模型，同时在非移动类智能体基准上有所提升且基本保持通用能力。
AI推荐理由 arXiv 预印本，作者团队规模大（含 Steven Hoi 等），摘要给出明确方法组件（AI for Data 数据飞轮、CARE 奖励工程、模型-工具协同演化）与 MobilePA-Bench 上的评测结论，信息密度较高。但仅有摘要级证据，未提供具体数值、消融或复现细节，且 MobilePA-Bench 为自建基准，结论的独立性有待验证，故未给更高分。
78
正文
Computer Science > Artificial Intelligence
arXiv:2609.29892 (cs)
[Submitted on 24 Sep 2026]
Title:Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents
Authors:Tingyu Qu, Weigao Sun, Yuecheng Liu, Yucheng Zhao, Yi Zhu, Yifeng Ding, Qiyi Wang, Sihan Cao, Pengkun Jiao, Hanlei Xie, Xiongwei Wu, Qichao Wang, Haodong Zhang, Jiajun Liu, Yuhao Wang, Yuqing Xie, Junpeng Zhao, Long Chen, Ming Ma, Sihan Yang, Ziwang Zhao, Yanhao Jia, Liangquan Gong, Feida Zhu, Yiran Zhong, Steven Hoi
View a PDF of the paper titled Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents, by Tingyu Qu and 25 other authors
View PDF
HTML (experimental)
Abstract:The rapid progression of large language models is extending AI from passive content generation into the active workflows of engineering and scientific discovery. This shift raises a compelling question: can AI be both the object of development and an active participant in building next-generation AI systems? We explore this question by building Qwen-Planner-Agent within a closed-loop AI-for-AI framework for scalable development and iterative improvement. Mobile planning offers a demanding test of this approach: complex, long-horizon tasks challenge agent reliability, while costly real-device interaction limits development scalability. The framework connects data production, model training, and deployment through a shared action-feedback-verification contract. (i) AI for Data builds a human-gated agentic data flywheel in which specialized agents construct tasks, collect interaction trajectories, curate and balance training data, and use training feedback to guide subsequent data generation. (ii) AI for Training combines a supervised planning cold start with hybrid-environment online agentic reinforcement learning, where we introduce Competence-Aware Reward-and-Advantage Engineering (CARE) to reduce reasoning and tool-use costs while preserving task performance. (iii) AI drives model--harness co-evolution through an execution-evidence-driven loop that orchestrates memory, skills, and tools at runtime and feeds structured action feedback and preserved failure traces back into coordinated model and harness adaptation. Qwen-Planner-Agent achieves the best overall performance among all evaluated models and systems on MobilePA-Bench, improving over its base model across tool use, memory, skills, and sub-agent coordination. Further evaluations of our model show improvements across non-mobile agentic benchmarks while largely preserving general capabilities.
Comments:
Subjects:
Artificial Intelligence (cs.AI)
Cite as:
arXiv:2609.29892 [cs.AI]
(or
arXiv:2609.29892v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.29892
Focus to learn more
arXiv-issued DOI via DataCite (pending registration)
Submission history
From: Tingyu Qu [view email]
[v1]
Thu, 24 Sep 2026 14:38:08 UTC (6,458 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Qwen-Planner-Agent: A Closed-Loop AI-for-AI Framework for Real-World Mobile Planner Agents, by Tingyu Qu and 25 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-09
Change to browse by:
cs
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)