paper-with-me

Papers

MEGA-GUI: Multi-stage Enhanced Grounding Agents for GUI Elements

2025-11-17 · SeokJoo Kwak, Jihoon Kim, Boyoun Kim, Jung Jae Yoon, Wooseok Jang, Jeonghoon Hong, Jaeho Yang, Yeong-Dae Kwon arxiv

Graphical User Interface (GUI) grounding - the task of mapping natural language instructions to screen coordinates - is essential for autonomous agents and accessibility technologies. Existing systems rely on monolithic models or one-shot pipelines that lack modularity and fail under visual clutter and ambiguous instructions. We introduce MEGA-GUI, a multi-stage framework that separates grounding into coarse Region-of-Interest (ROI) selection and fine-grained element grounding, orchestrated by specialized vision-language agents. MEGA-GUI features a bidirectional ROI zoom algorithm that mitigates spatial dilution and a context-aware rewriting agent that reduces semantic ambiguity. Our analysis reveals complementary strengths and weaknesses across vision-language models at different visual scales, and we show that leveraging this modular structure achieves consistently higher accuracy than monolithic approaches. On the visually dense ScreenSpot-Pro benchmark, MEGA-GUI attains 73.18% accuracy, and on the semantically complex OSWorld-G benchmark it reaches 68.63%, surpassing previously reported results. Code and the Grounding Benchmark Toolkit (GBT) are available at https://github.com/samsungsds-research-papers/mega-gui.

📄 PDF Abstract BibTeX arXiv:2511.13087

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

OmegaUse-OfficeVal: Benchmarking LLM Agents on Long-Horizon Office-Suite Tasks with Economic Grounding

2026-07-29 · Jingbo Zhou, Yusai Zhao, Qi Bao, Jingjia Cao 외 hf

Large language model (LLM) agents are increasingly expected to assist users in completing tasks. However, existing benchmarks provide limited support for evaluating whether agents can carry out office-suite workflows at …

MM-StanceDet: Retrieval-Augmented Multi-modal Multi-agent Stance Detection

2026-04-30 · Weihai Lu, Zhejun Zhao, Yanshu Li, Huan He arxiv

Multimodal Stance Detection (MSD) is crucial for understanding public discourse, yet effectively fusing text and image, especially with conflicting signals, remains challenging. Existing methods often face difficulties w…

Stance Detection

OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution

2026-01-28 · Le Zhang, Yixiong Xiao, Xinjiang Lu, Jingjia Cao 외 arxiv

Graphical User Interface (GUI) agents show great potential for enabling foundation models to complete real-world tasks, revolutionizing human-computer interaction and improving human productivity. In this report, we pres…

Computational Efficiency

Removing Data Heterogeneity Influence Enhances Network Topology Dependence of Decentralized SGD

2021-05-17 · Kun Yuan, Sulaiman A. Alghunaim, Xinmeng Huang

We consider the decentralized stochastic optimization problems, where a network of $n$ nodes, each owning a local cost function, cooperate to find a minimizer of the globally-averaged cost. A widely studied decentralized…

Stochastic Optimization

Smoothing Grounding and Reasoning for MLLM-Powered GUI Agents with Query-Oriented Pivot Tasks

2025-03-01 · Zongru Wu, Pengzhou Cheng, Zheng Wu, Tianjie Ju 외

Perception-enhanced pre-training, particularly through grounding techniques, is widely adopted to enhance the performance of graphical user interface (GUI) agents. However, in resource-constrained scenarios, the format d…