GAIA: A Data Flywheel System for Training GUI Test-Time Scaling Critic Models

TL;DR

GAIA introduces a training framework that iteratively improves GUI agent performance by using a critic model to evaluate and refine actions, enabling self-improvement and better handling of errors during task execution.

Contribution

The paper presents GAIA, a novel data flywheel system that trains an intuitive critic model to enhance GUI agent performance through iterative self-improvement cycles.

Findings

ICM improves test-time performance of GUI agents

Performance increases as data is recycled through the system

Effective on both open-source and closed-source models

Abstract

While Large Vision-Language Models (LVLMs) have significantly advanced GUI agents' capabilities in parsing textual instructions, interpreting screen content, and executing tasks, a critical challenge persists: the irreversibility of agent operations, where a single erroneous action can trigger catastrophic deviations. To address this, we propose the GUI Action Critic's Data Flywheel System (GAIA), a training framework that enables the models to have iterative critic capabilities, which are used to improve the Test-Time Scaling (TTS) of basic GUI agents' performance. Specifically, we train an Intuitive Critic Model (ICM) using positive and negative action examples from a base agent first. This critic evaluates the immediate correctness of the agent's intended actions, thereby selecting operations with higher success probability. Then, the initial critic guides agent actions to collect refined positive/negative samples, initiating the self-improving cycle. The augmented data then trains a second-round critic with enhanced discernment capability. We conduct experiments on various datasets and demonstrate that the proposed ICM can improve the test-time performance of various closed-source and open-source models, and the performance can be gradually improved as the data is recycled. The code and dataset will be publicly released.