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智能体代表了人机交互领域的重要演进，有望降低认知负荷并优化工作流程。然而，现有数据集存在两个关键缺陷：(1) 依赖LLM合成数据，无法捕捉真实的人类决策模式；(2) 聚焦于孤立任务而非连续工作流，缺失了学习主动干预信号所必需的事前辅助行为上下文。为弥补这些不足，我们提出了ProAgentBench——一个面向工作场景中主动智能体的严谨基准。我们的贡献包括：(1) 将主动辅助分解为时机预测与辅助内容生成的分层任务框架；(2) 包含500+小时真实用户会话中28,000+事件的隐私合规数据集，保留了合成数据中缺失的突发交互模式（突发性B=0.787）；(3) 对基于LLM和VLM的基线模型进行广泛实验。数值实验表明，长期记忆与历史上下文能显著提升预测准确率，而真实世界训练数据明显优于合成数据。我们在https://anonymous.4open.science/r/ProAgentBench-6BC0公开了数据集与代码。