AFRAgent : An Adaptive Feature Renormalization Based High Resolution Aware GUI agent

TL;DR

AFRAgent is a compact multimodal GUI automation model that uses adaptive feature renormalization to improve widget identification and task execution, achieving state-of-the-art results on smartphone automation benchmarks.

Contribution

This work introduces AFRAgent, a novel, smaller multimodal architecture with adaptive feature renormalization that enhances image embeddings for GUI automation tasks.

Findings

Achieves superior performance on Meta-GUI and AITW benchmarks.

Less than one-fourth the size of comparable models.

Establishes new state-of-the-art in smartphone automation.

Abstract

There is a growing demand for mobile user interface (UI) automation, driven by its broad applications across industries. With the advent of visual language models (VLMs), GUI automation has progressed from generating text-based instructions for humans to autonomously executing tasks, thus optimizing automation workflows. Recent approaches leverage VLMs for this problem due to their ability to 1) process on-screen content directly, 2) remain independent of device-specific APIs by utilizing human actions (e.g., clicks, typing), and 3) apply real-world contextual knowledge for task understanding. However, these models often have trouble accurately identifying widgets and determining actions due to limited spatial information in vision encoder features. Additionally, top-performing models are often large, requiring extensive training and resulting in inference delays. In this work, we introduce AFRAgent, an instruct-BLIP-based multimodal architecture that achieves superior performance in GUI automation while being less than one-fourth the size of its nearest competitor. To enhance image embeddings in the large language model (LLM) pipeline, we propose an adaptive feature renormalization-based (a token-level affine transformation) technique that effectively enriches low-resolution image embeddings and fuses high-resolution details. We evaluate AFRAgent on Meta-GUI and AITW benchmarks, establishing a new state-of-the-art baseline for smartphone automation.