Ponder & Press: Advancing Visual GUI Agent towards General Computer Control

TL;DR

Ponder & Press introduces a visual-only GUI agent framework that combines large language models to accurately interpret user instructions and locate GUI elements, enabling versatile and human-like computer control across diverse environments.

Contribution

The paper presents a novel divide-and-conquer framework using multimodal large language models for visual GUI control, outperforming existing models in GUI grounding and interaction benchmarks.

Findings

Outperforms existing models by +22.5% on ScreenSpot GUI grounding benchmark.

Achieves state-of-the-art performance across web, desktop, and mobile UIs.

Demonstrates versatile, human-like interaction using only visual input.

Abstract

Most existing GUI agents typically depend on non-vision inputs like HTML source code or accessibility trees, limiting their flexibility across diverse software environments and platforms. Current multimodal large language models (MLLMs), which excel at using vision to ground real-world objects, offer a potential alternative. However, they often struggle with accurately localizing GUI elements -- a critical requirement for effective GUI automation -- due to the semantic gap between real-world objects and GUI elements. In this work, we introduce Ponder & Press, a divide-and-conquer framework for general computer control using only visual input. Our approach combines an general-purpose MLLM as an 'interpreter', responsible for translating high-level user instructions into detailed action descriptions, with a GUI-specific MLLM as a 'locator' that precisely locates GUI elements for action placement. By leveraging a purely visual input, our agent offers a versatile, human-like interaction paradigm applicable to a wide range of applications. Ponder & Press locator outperforms existing models by +22.5% on the ScreenSpot GUI grounding benchmark. Both offline and interactive agent benchmarks across various GUI environments -- including web pages, desktop software, and mobile UIs -- demonstrate that Ponder & Press framework achieves state-of-the-art performance, highlighting the potential of visual GUI agents. Refer to the project homepage https://invinciblewyq.github.io/ponder-press-page/