paper-with-me

Papers

ClickAgent: Enhancing UI Location Capabilities of Autonomous Agents

2024-10-09 · Jakub Hoscilowicz, Bartosz Maj, Bartosz Kozakiewicz, Oleksii Tymoshchuk, Artur Janicki

With the growing reliance on digital devices equipped with graphical user interfaces (GUIs), such as computers and smartphones, the need for effective automation tools has become increasingly important. While multimodal large language models (MLLMs) like GPT-4V excel in many areas, they struggle with GUI interactions, limiting their effectiveness in automating everyday tasks. In this paper, we introduce ClickAgent, a novel framework for building autonomous agents. In ClickAgent, the MLLM handles reasoning and action planning, while a separate UI location model (e.g., SeeClick) identifies the relevant UI elements on the screen. This approach addresses a key limitation of current-generation MLLMs: their difficulty in accurately locating UI elements. ClickAgent outperforms other prompt-based autonomous agents (CogAgent, AppAgent) on the AITW benchmark. Our evaluation was conducted on both an Android smartphone emulator and an actual Android smartphone, using the task success rate as the key metric for measuring agent performance.

📄 PDF Abstract BibTeX arXiv:2410.11872

Code (1)

Samsung/ClickAgent 공식 구현 pytorch

Similar Papers 제목 키워드 기반

Towards Autonomous Agents: Adaptive-planning, Reasoning, and Acting in Language Models

2024-08-12 · Abhishek Dutta, Yen-Che Hsiao

We propose a novel in-context learning algorithm for building autonomous decision-making language agents. The language agent continuously attempts to solve the same task by self-correcting each time the task fails. Our s…

Decision MakingIn-Context LearningLanguage ModelingLanguage Modelling

Mantis: Enabling Energy-Efficient Autonomous Mobile Agents with Spiking Neural Networks

2022-12-24 · Rachmad Vidya Wicaksana Putra, Muhammad Shafique

Autonomous mobile agents such as unmanned aerial vehicles (UAVs) and mobile robots have shown huge potential for improving human productivity. These mobile agents require low power/energy consumption to have a long lifes…

Model Selection

SkillWeaver: Web Agents can Self-Improve by Discovering and Honing Skills

2025-04-09 · Boyuan Zheng, Michael Y. Fatemi, Xiaolong Jin, Zora Zhiruo Wang 외

To survive and thrive in complex environments, humans have evolved sophisticated self-improvement mechanisms through environment exploration, hierarchical abstraction of experiences into reuseable skills, and collaborati…

Enhancing Trust in Autonomous Agents: An Architecture for Accountability and Explainability through Blockchain and Large Language Models

2024-03-14 · Laura Fernández-Becerra, Miguel Ángel González-Santamarta, Ángel Manuel Guerrero-Higueras, Francisco Javier Rodríguez-Lera 외

The deployment of autonomous agents in environments involving human interaction has increasingly raised security concerns. Consequently, understanding the circumstances behind an event becomes critical, requiring the dev…

LLMArena: Assessing Capabilities of Large Language Models in Dynamic Multi-Agent Environments

2024-02-26 · Junzhe Chen, Xuming Hu, Shuodi Liu, Shiyu Huang 외

Recent advancements in large language models (LLMs) have revealed their potential for achieving autonomous agents possessing human-level intelligence. However, existing benchmarks for evaluating LLM Agents either use sta…

Spatial Reasoning