AIMar 5, 2024

Cradle: Empowering Foundation Agents Towards General Computer Control

arXiv:2403.03186v398 citationsh-index: 19
Originality Incremental advance
AI Analysis

This addresses the problem of limited generalizability in foundation agents for researchers and developers, enabling broader application to software and games, though it is incremental as it builds on existing LMM-powered frameworks.

The paper tackles the challenge of foundation agents struggling to generalize across virtual scenarios by proposing the General Computer Control (GCC) setting, which uses screenshots as input and keyboard/mouse actions as output, and introduces Cradle, a framework that achieves impressive performance in tasks like completing 40-minute missions in Red Dead Redemption 2 and achieving an 87% weekly profit in Dealer's Life 2.

Despite the success in specific scenarios, existing foundation agents still struggle to generalize across various virtual scenarios, mainly due to the dramatically different encapsulations of environments with manually designed observation and action spaces. To handle this issue, we propose the General Computer Control (GCC) setting to restrict foundation agents to interact with software through the most unified and standardized interface, i.e., using screenshots as input and keyboard and mouse actions as output. We introduce Cradle, a modular and flexible LMM-powered framework, as a preliminary attempt towards GCC. Enhanced by six key modules, Cradle can understand input screenshots and output executable code for low-level keyboard and mouse control after high-level planning, so that Cradle can interact with any software and complete long-horizon complex tasks without relying on any built-in APIs. Experimental results show that Cradle exhibits remarkable generalizability and impressive performance across four previously unexplored commercial video games, five software applications, and a comprehensive benchmark, OSWorld. Cradle is the first to enable foundation agents to follow the main storyline and complete 40-minute-long real missions in the complex AAA game Red Dead Redemption 2 (RDR2). Cradle can also create a city of a thousand people in Cities: Skylines, farm and harvest parsnips in Stardew Valley, and trade and bargain with a maximal weekly total profit of 87% in Dealer's Life 2. Cradle can not only operate daily software, like Chrome, Outlook, and Feishu, but also edit images and videos using Meitu and CapCut. Cradle greatly extends the reach of foundation agents by enabling the easy conversion of any software, especially complex games, into benchmarks to evaluate agents' various abilities and facilitate further data collection, thus paving the way for generalist agents.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes