paper-with-me

홈 › Papers

BlueLM-GUI Technical Report: A Real-Device-Centric Flywheel for Self-Improving Mobile GUI Agents

2026-09-11 · Tong Ye, Kunyang Han, Guozhi Wang, Longqiang Luo, Zhifeng Ding, Yongxiang Zhang, Xiaolei Shen, Yuxuan Zhang, Zhuping Zhang, Tao Xu, Yue Pan, Yucheng Zhao, Yupei Hu, Yuanjiang Ouyang, Danfeng Shen, Runqi Lin, Hongda Cai, Zhaoxiong Wang, Mengjia Yan, Yingjie Zhong, Chen Zhou, Zeyu Zhang, Xuwen Zhu, Penggang Shi, Mingcheng Luo, Ziyang Wu, Min Jin, Mingfu Shen, Zairong Xu, Fan Zhang, Hao Wang, Liang Liu, Zhulin Xie, Lijun Yao, Xiao Liang, Liangmin Wen, Liqiang Feng, Feilong Wu, Min Hu, Min Chen, Guanjing Xiong, Xiaohu Ruan, Xiaoxin Chen arxiv

Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent gaps. Sandbox training produces a distribution mismatch with production environments; expensive real-device failures remain underutilized; and fixed benchmarks saturate, losing the power to guide iteration. We present BlueLM-GUI, a 35B-A3B mobile GUI agent built as a real-device-centric flywheel that closes these gaps through three principles. Every Sample Matters: a dual-track pipeline with Heterogeneous Triple-System Consensus evaluation and an Error Correction \& Derivation Module salvages every trajectory into usable supervision. Every Rollout Is Real: a three-stage recipe---continual pre-training, supervised fine-tuning, and agentic reinforcement learning on hundreds of real phones---grounds every rollout in real production environments, so the capability the model learns transfers directly to deployment. Every Query Evolves: a quota-driven benchmark methodology with three orthogonal axes enables precise attribution and allows the benchmark to be systematically upgraded as the model improves. BlueLM-GUI achieves 87.4 on MobileGUI-VBench, surpassing the best closed-source model by 5.1 points, and 84.9 on AndroidWorld, the best result among open-source models and competitive with closed-source models. These results demonstrate that grounding model training and iterative improvement in both real devices and the three Every principles yields strong, robust, and transferable mobile GUI capability.

📄 PDF Abstract BibTeX arXiv:2609.12394

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

BlueLM-2.5-3B Technical Report

2025-07-08 · Baojiao Xiong, Boheng Chen, Chengzhi Wang, Daxiong Luo 외

We present BlueLM-2.5-3B, a compact and unified dense Multimodal Large Language Model (MLLM) designed for efficient edge-device deployment, offering strong general-purpose and reasoning capabilities. To the best of our k…

Large Language ModelMultimodal Large Language Model

BlueLM-V-3B: Algorithm and System Co-Design for Multimodal Large Language Models on Mobile Devices

2024-11-16 · CVPR 2025 1 · Xudong Lu, Yinghao Chen, Cheng Chen, Hui Tan 외

The emergence and growing popularity of multimodal large language models (MLLMs) have significant potential to enhance various aspects of daily life, from improving communication to facilitating learning and problem-solv…

Quantization

Qwen-UI-Agent Technical Report: Toward Next-Generation Real-World Centric Foundation GUI Agents

2026-07-30 · Hanzhang Zhou, Panrong Tong, Xu Zhang, Quyu Kong 외 arxiv

GUI agents have the potential to become a general purpose executor over existing digital devices. To advance them toward real-world use, we envision agents that operate reliably on real devices, execute workflows across …

MEEV: Body Mesh Estimation On Egocentric Video

2022-10-21 · Nicolas Monet, Dongyoon Wee

This technical report introduces our solution, MEEV, proposed to the EgoBody Challenge at ECCV 2022. Captured from head-mounted devices, the dataset consists of human body shape and motion of interacting people. The EgoB…

3D human pose and shape estimation3D Human Pose Estimation3D Pose EstimationPose Estimation

HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction

2022-06-24 · Zhenpei Yang, Zaiwei Zhang, QiXing Huang

Reconstructing 3D objects is an important computer vision task that has wide application in AR/VR. Deep learning algorithm developed for this task usually relies on an unrealistic synthetic dataset, such as ShapeNet and …

3D ReconstructionCamera Pose EstimationDataset GenerationMulti-View 3D Reconstruction+3