InfiniteWeb: Scalable Web Environment Synthesis for GUI Agent Training

TL;DR

InfiniteWeb is a system that automatically generates large-scale, functional web environments to facilitate training GUI agents, overcoming environment scarcity and improving agent performance.

Contribution

The paper introduces InfiniteWeb, a novel system for scalable, realistic web environment generation, enabling effective GUI agent training with verifiable task evaluators.

Findings

InfiniteWeb outperforms commercial coding agents in website construction tasks.

Agents trained on InfiniteWeb environments show significant performance gains on benchmark tasks.

The system provides dense reward signals through verifiable task evaluators.

Abstract

GUI agents that interact with graphical interfaces on behalf of users represent a promising direction for practical AI assistants. However, training such agents is hindered by the scarcity of suitable environments. We present InfiniteWeb, a system that automatically generates functional web environments at scale for GUI agent training. While LLMs perform well on generating a single webpage, building a realistic and functional website with many interconnected pages faces challenges. We address these challenges through unified specification, task-centric test-driven development, and a combination of website seed with reference design image to ensure diversity. Our system also generates verifiable task evaluators enabling dense reward signals for reinforcement learning. Experiments show that InfiniteWeb surpasses commercial coding agents at realistic website construction, and GUI agents trained on our generated environments achieve significant performance improvements on OSWorld and Online-Mind2Web, demonstrating the effectiveness of proposed system.