Surfer 2：新一代跨平台計算機使用代理

摘要

建構能夠在網頁、桌面及行動裝置環境間通用化的智慧體仍是開放性挑戰，現有系統多依賴特定環境介面而限制跨平台部署。我們提出Surfer 2——純粹基於視覺觀測的統一架構，在三類環境中均實現最先進效能。該架構整合階層式情境管理、解耦的規劃與執行模組，以及具備自適應恢復機制的自我驗證功能，從而在長時序任務中實現可靠操作。我們的系統在WebVoyager達到97.1%準確率、WebArena達69.6%、OSWorld達60.1%、AndroidWorld達87.1%，無需任務特定微調即超越所有既有系統。透過多重嘗試機制，Surfer 2在所有基準測試中均超越人類表現。這些成果證明系統化協調機制能放大基礎模型能力，實現純視覺互動的通用電腦控制，同時呼籲需發展新一代視覺語言模型以達成帕雷托最優的成本效益。

English

Building agents that generalize across web, desktop, and mobile environments remains an open challenge, as prior systems rely on environment-specific interfaces that limit cross-platform deployment. We introduce Surfer 2, a unified architecture operating purely from visual observations that achieves state-of-the-art performance across all three environments. Surfer 2 integrates hierarchical context management, decoupled planning and execution, and self-verification with adaptive recovery, enabling reliable operation over long task horizons. Our system achieves 97.1% accuracy on WebVoyager, 69.6% on WebArena, 60.1% on OSWorld, and 87.1% on AndroidWorld, outperforming all prior systems without task-specific fine-tuning. With multiple attempts, Surfer 2 exceeds human performance on all benchmarks. These results demonstrate that systematic orchestration amplifies foundation model capabilities and enables general-purpose computer control through visual interaction alone, while calling for a next-generation vision language model to achieve Pareto-optimal cost-efficiency.

Surfer 2：新一代跨平台計算機使用代理

Surfer 2: The Next Generation of Cross-Platform Computer Use Agents

摘要

Support