paper-with-me

Papers

Less is More: Empowering GUI Agent with Context-Aware Simplification

2025-07-04 · Gongwei Chen, Xurui Zhou, Rui Shao, Yibo Lyu, Kaiwen Zhou, Shuai Wang, Wentao Li, Yinchuan Li, Zhongang Qi, Liqiang Nie arxiv

The research focus of GUI agents is shifting from text-dependent to pure-vision-based approaches, which, though promising, prioritize comprehensive pre-training data collection while neglecting contextual modeling challenges. We probe the characteristics of element and history contextual modeling in GUI agent and summarize: 1) the high-density and loose-relation of element context highlight the existence of many unrelated elements and their negative influence; 2) the high redundancy of history context reveals the inefficient history modeling in current GUI agents. In this work, we propose a context-aware simplification framework for building an efficient and effective GUI Agent, termed SimpAgent. To mitigate potential interference from numerous unrelated elements, we introduce a masking-based element pruning method that circumvents the intractable relation modeling through an efficient masking mechanism. To reduce the redundancy in historical information, we devise a consistency-guided history compression module, which enhances implicit LLM-based compression through innovative explicit guidance, achieving an optimal balance between performance and efficiency. With the above components, SimpAgent reduces 27% FLOPs and achieves superior GUI navigation performances. Comprehensive navigation experiments across diverse web and mobile environments demonstrate the effectiveness and potential of our agent.

📄 PDF Abstract BibTeX arXiv:2507.03730

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management

2025-08-06 · Mo Li, L. H. Xu, Qitai Tan, Long Ma 외 arxiv

Large Language Models (LLMs) suffer from significant performance degradation when processing long contexts due to proactive interference, where irrelevant information in earlier parts of the context disrupts reasoning an…

Reinforcement Learning

Empowering LLM Agents with Geospatial Awareness: Toward Grounded Reasoning for Wildfire Response

2025-10-14 · Yiheng Chen, Lingyao Li, Zihui Ma, Qikai Hu 외 arxiv

Effective disaster response is essential for safeguarding lives and property. Existing statistical approaches often lack semantic context, generalize poorly across events, and offer limited interpretability. While Large …

Bias-Aware Agent: Enhancing Fairness in AI-Driven Knowledge Retrieval

2025-03-27 · Karanbir Singh, William Ngu

Advancements in retrieving accessible information have evolved faster in the last few years compared to the decades since the internet's creation. Search engines, like Google, have been the number one way to find relevan…

FairnessInformation RetrievalRetrieval

TalkUp: Paving the Way for Understanding Empowering Language

2023-05-23 · Lucille Njoo, Chan Young Park, Octavia Stappart, Marvin Thielk 외

Empowering language is important in many real-world contexts, from education to workplace dynamics to healthcare. Though language technologies are growing more prevalent in these contexts, empowerment has seldom been stu…

CaMML: Context-Aware Multimodal Learner for Large Models

2024-01-06 · Yixin Chen, Shuai Zhang, Boran Han, Tong He 외

In this work, we introduce Context-Aware MultiModal Learner (CaMML), for tuning large multimodal models (LMMs). CaMML, a lightweight module, is crafted to seamlessly integrate multimodal contextual samples into large mod…

Visual Question Answering