AutoGLM: Autonomous Foundation Agents for GUIs

TL;DR

AutoGLM is an autonomous foundation agent system designed for GUI interactions, enabling decision-making and control in web and mobile environments through innovative training and interface techniques.

Contribution

The paper introduces AutoGLM, a novel foundation agent system with a new intermediate interface design and a progressive self-evolving reinforcement learning framework for real-world GUI control.

Findings

Achieves 55.2% success on VAB-WebArena-Lite, improving to 59.1% with retries.

Attains 96.2% success on OpenTable tasks.

Reaches 89.7% success on common Chinese app tasks.

Abstract

We present AutoGLM, a new series in the ChatGLM family, designed to serve as foundation agents for autonomous control of digital devices through Graphical User Interfaces (GUIs). While foundation models excel at acquiring human knowledge, they often struggle with decision-making in dynamic real-world environments, limiting their progress toward artificial general intelligence. This limitation underscores the importance of developing foundation agents capable of learning through autonomous environmental interactions by reinforcing existing models. Focusing on Web Browser and Phone as representative GUI scenarios, we have developed AutoGLM as a practical foundation agent system for real-world GUI interactions. Our approach integrates a comprehensive suite of techniques and infrastructures to create deployable agent systems suitable for user delivery. Through this development, we have derived two key insights: First, the design of an appropriate "intermediate interface" for GUI control is crucial, enabling the separation of planning and grounding behaviors, which require distinct optimization for flexibility and accuracy respectively. Second, we have developed a novel progressive training framework that enables self-evolving online curriculum reinforcement learning for AutoGLM. Our evaluations demonstrate AutoGLM's effectiveness across multiple domains. For web browsing, AutoGLM achieves a 55.2% success rate on VAB-WebArena-Lite (improving to 59.1% with a second attempt) and 96.2% on OpenTable evaluation tasks. In Android device control, AutoGLM attains a 36.2% success rate on AndroidLab (VAB-Mobile) and 89.7% on common tasks in popular Chinese APPs.