EnterpriseClawBench：從真實工作場景中評測代理

摘要

企業級代理日益在實際工作環境中運作：它們讀取異質檔案、呼叫工具、產出商業成果。我們提出EnterpriseClawBench，這是一個基於專有真實代理對話所建構的企業級代理基準。從大量工作環境對話資料庫出發，EnterpriseClawBench 產出了 852 項可重現任務，每項任務都配有還原後的測試資源、改寫後的提示、角色類別、技能子類別、硬性規則與語義評估準則。由於這些對話包含企業內部內容，我們未公開基準資料；相反地，我們可重複使用的貢獻在於其建構流程與評估協議。在 EnterpriseClawBench 上，最佳配置僅達到 0.663（Codex 搭配 GPT-5.5）。這項結果顯示，企業級代理評估必須報告測試框架與模型組合、成果交付、視覺品質、成本、執行時間與技能遷移行為，而不應將效能簡化為單一分數。程式碼：https://github.com/FrontisAI/EnterpriseClawBench

English

Enterprise agents increasingly operate inside workspaces: they read heterogeneous files, invoke tools, and deliver business artifacts. We introduce EnterpriseClawBench, an enterprise agent benchmark constructed from proprietary, real-world agent sessions. Starting from a large archive of workplace sessions, the EnterpriseClawBench produces 852 reproducible tasks, each paired with recovered fixtures, rewritten prompts, role classes, skill subclasses, hard rules, and semantic rubrics. Because the sessions contain internal enterprise content, we do not release the benchmark data; instead, our reusable contribution is the construction and evaluation protocol. On EnterpriseClawBench, the best configuration reaches only 0.663 (Codex with GPT-5.5). These results show that enterprise agent evaluation must report harness--model combinations, artifact delivery, visual quality, cost, runtime, and skill-transfer behavior, rather than collapsing performance into a single score. Code: https://github.com/FrontisAI/EnterpriseClawBench