Proactive agents that anticipate user intentions without explicit prompts represent a significant evolution in human-AI interaction, promising to reduce cognitive load and streamline workflows. However, existing datasets suffer from two critical deficiencies: (1) reliance on LLM-synthesized data that fails to capture authentic human decision-making patterns, and (2) focus on isolated tasks rather than continuous workflows, missing the pre-assistance behavioral context essential for learning proactive intervention signals. To address these gaps, we introduce ProAgentBench, a rigorous benchmark for proactive agents in working scenarios. Our contributions include: (1) a hierarchical task framework that decomposes proactive assistance into timing prediction and assist content generation; (2) a privacy-compliant dataset with 28,000+ events from 500+ hours of real user sessions, preserving bursty interaction patterns (burstiness B=0.787) absent in synthetic data; and (3) extensive experiments that evaluates LLM- and VLM-based baselines. Numerically, we showed that long-term memory and historical context significantly enhance prediction accuracy, while real-world training data substantially outperforms synthetic alternatives. We release our dataset and code at https://anonymous.4open.science/r/ProAgentBench-6BC0.

翻译：无需明确提示即可预测用户意图的主动助手机器人代表了人机交互领域的重大进展，有望降低认知负荷并简化工作流程。然而，现有数据集存在两个关键缺陷：(1) 依赖LLM合成的数据，无法捕捉真实的人类决策模式；(2) 侧重于孤立任务而非连续工作流程，遗漏了学习主动干预信号所必需的预协助行为上下文。为弥补这些不足，我们提出了ProAgentBench，一个面向工作场景中主动助手机器人的严格基准。我们的贡献包括：(1) 一个将主动协助分解为时机预测与协助内容生成的分层任务框架；(2) 一个符合隐私规范的、包含来自500多小时真实用户会话的28,000多个事件的数据集，保留了合成数据中缺失的突发交互模式（突发性B=0.787）；以及(3) 对基于LLM和VLM的基线模型进行了广泛实验。数值结果表明，长期记忆和历史上下文能显著提升预测准确性，而真实世界训练数据则大幅优于合成替代方案。我们在https://anonymous.4open.science/r/ProAgentBench-6BC0 发布了数据集与代码。