Cradle: Empowering Foundation Agents Towards General Computer Control

• URL: http://arxiv.org/abs/2403.03186v3
• Date: Tue, 2 Jul 2024 17:23:13 GMT
• Title: Cradle: Empowering Foundation Agents Towards General Computer Control
• Authors: Weihao Tan, Wentao Zhang, Xinrun Xu, Haochong Xia, Ziluo Ding, Boyu Li, Bohan Zhou, Junpeng Yue, Jiechuan Jiang, Yewen Li, Ruyi An, Molei Qin, Chuqiao Zong, Longtao Zheng, Yujie Wu, Xiaoqiang Chai, Yifei Bi, Tianbao Xie, Pengjie Gu, Xiyun Li, Ceyao Zhang, Long Tian, Chaojie Wang, Xinrun Wang, Börje F. Karlsson, Bo An, Shuicheng Yan, Zongqing Lu,
• Abstract summary: We introduce Cradle, a modular and flexible LMM-powered framework, as a preliminary attempt towards GCC. Cradle can understand input screenshots and output executable code for low-level keyboard and mouse control after high-level planning. Cradle exhibits remarkable generalizability and impressive performance across four previously unexplored commercial video games, five software applications, and a comprehensive benchmark, OSWorld.
• Score: 80.02794667853045
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Game-TARS: Pretrained Foundation Models for Scalable Generalist Multimodal Game Agents [56.25101378553328]
  We present Game-TARS, a generalist game agent trained with a unified, scalable action space anchored to human-aligned keyboard-mouse inputs.<n>Game-TARS is pre-trained on over 500B tokens with diverse trajectories and multimodal data.<n> Experiments show that Game-TARS achieves about 2 times the success rate over the previous sota model on open-world Minecraft tasks.
  arXiv  Detail & Related papers  (2025-10-27T17:43:51Z)
• M4Diffuser: Multi-View Diffusion Policy with Manipulability-Aware Control for Robust Mobile Manipulation [17.9979990426915]
  M4Diffuser is a hybrid framework that integrates a Multi-View Diffusion Policy with a novel Reduced and Manipulability-aware QP controller for mobile manipulation.<n>Our approach demonstrates robust performance for smooth whole-body coordination, and strong generalization to unseen tasks.
  arXiv  Detail & Related papers  (2025-09-18T14:09:53Z)
• MagicGUI: A Foundational Mobile GUI Agent with Scalable Data Pipeline and Reinforcement Fine-tuning [83.81404871748438]
  MagicGUI is a foundational mobile GUI agent designed to address critical challenges in perception, grounding, and reasoning within real-world mobile GUI environments.<n>The framework is underpinned by six key components, including a comprehensive and accurate dataset, enhanced perception and grounding capabilities, a comprehensive and unified action space, and planning-oriented reasoning mechanisms.
  arXiv  Detail & Related papers  (2025-07-19T12:33:43Z)
• Scaling Computer-Use Grounding via User Interface Decomposition and Synthesis [59.83524388782554]
  Graphical user interface (GUI) grounding remains a critical bottleneck in computer use agent development.<n>We introduce OSWorld-G, a comprehensive benchmark comprising 564 finely annotated samples across diverse task types.<n>We synthesize and release the largest computer use grounding dataset Jedi, which contains 4 million examples.
  arXiv  Detail & Related papers  (2025-05-19T15:09:23Z)
• QuadWBG: Generalizable Quadrupedal Whole-Body Grasping [7.802964645500815]
  We present a modular framework for robust whole-body loco-manipulation controller based on a single arm-mounted camera. The proposed system achieves state-of-the-art one-time grasping accuracy of 89% in the real world.
  arXiv  Detail & Related papers  (2024-11-11T08:19:54Z)
• CRAB: Cross-environment Agent Benchmark for Multimodal Language Model Agents [49.68117560675367]
  Crab is the first benchmark framework designed to support cross-environment tasks. Our framework supports multiple devices and can be easily extended to any environment with a Python interface. The experimental results demonstrate that the single agent with GPT-4o achieves the best completion ratio of 38.01%.
  arXiv  Detail & Related papers  (2024-07-01T17:55:04Z)
• OS-Copilot: Towards Generalist Computer Agents with Self-Improvement [48.29860831901484]
  We introduce OS-Copilot, a framework to build generalist agents capable of interfacing with comprehensive elements in an operating system (OS) We use OS-Copilot to create FRIDAY, a self-improving embodied agent for automating general computer tasks. On GAIA, a general AI assistants benchmark, FRIDAY outperforms previous methods by 35%, showcasing strong generalization to unseen applications via accumulated skills from previous tasks.
  arXiv  Detail & Related papers  (2024-02-12T07:29:22Z)
• ScreenAgent: A Vision Language Model-driven Computer Control Agent [17.11085071288194]
  We build an environment for a Vision Language Model (VLM) agent to interact with a real computer screen. Within this environment, the agent can observe screenshots and manipulate the Graphics User Interface (GUI) by outputting mouse and keyboard actions. We construct the ScreenAgent dataset, which collects screenshots and action sequences when completing a variety of daily computer tasks.
  arXiv  Detail & Related papers  (2024-02-09T02:33:45Z)
• Octopus: Embodied Vision-Language Programmer from Environmental Feedback [58.04529328728999]
  Embodied vision-language models (VLMs) have achieved substantial progress in multimodal perception and reasoning. To bridge this gap, we introduce Octopus, an embodied vision-language programmer that uses executable code generation as a medium to connect planning and manipulation. Octopus is designed to 1) proficiently comprehend an agent's visual and textual task objectives, 2) formulate intricate action sequences, and 3) generate executable code.
  arXiv  Detail & Related papers  (2023-10-12T17:59:58Z)
• MindAgent: Emergent Gaming Interaction [103.73707345211892]
  Large Language Models (LLMs) have the capacity of performing complex scheduling in a multi-agent system. We propose MindAgent to evaluate planning and coordination emergent capabilities for gaming interaction.
  arXiv  Detail & Related papers  (2023-09-18T17:52:22Z)
• Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory [97.87093169454431]
  Ghost in the Minecraft (GITM) is a novel framework that integrates Large Language Models (LLMs) with text-based knowledge and memory. We develop a set of structured actions and leverage LLMs to generate action plans for the agents to execute. The resulting LLM-based agent markedly surpasses previous methods, achieving a remarkable improvement of +47.5% in success rate.
  arXiv  Detail & Related papers  (2023-05-25T17:59:49Z)
• ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills [24.150758623016195]
  We present ManiSkill2, the next generation of the SAPIEN ManiSkill benchmark for generalizable manipulation skills. ManiSkill2 includes 20 manipulation task families with 2000+ object models and 4M+ demonstration frames. It defines a unified interface and evaluation protocol to support a wide range of algorithms. It empowers fast visual input learning algorithms so that a CNN-based policy can collect samples at about 2000 FPS.
  arXiv  Detail & Related papers  (2023-02-09T14:24:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.