模拟网络智能体中的人类差异化交互

摘要

尽管自主网页代理发展迅速，但在任务执行过程中，人类参与对于设定偏好和修正代理行为仍不可或缺。然而现有代理系统缺乏对人类干预时机与动机的理论认知，往往在跨越关键决策点时仍自主运行，或提出不必要的确认请求。本研究提出建立人类干预模型以支持协作式网页任务执行的新任务。我们收集了包含4200余项交错式人机操作的400条真实用户网页导航轨迹数据集CowCorpus，并识别出用户与代理互作的四种典型模式——放手监督、动手监察、协作解题及完全接管。基于这些发现，我们训练语言模型根据用户交互风格预测其干预倾向，使干预预测准确率较基础语言模型提升61.4-63.4%。最终将这类具备干预感知能力的模型部署至实时网页导航代理，通过用户研究发现代理可用性评分提升26.5%。研究表明：对人类干预进行结构化建模能有效增强代理的适应性与协作能力。

English

Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why humans intervene, often proceeding autonomously past critical decision points or requesting unnecessary confirmation. In this work, we introduce the task of modeling human intervention to support collaborative web task execution. We collect CowCorpus, a dataset of 400 real-user web navigation trajectories containing over 4,200 interleaved human and agent actions. We identify four distinct patterns of user interaction with agents -- hands-off supervision, hands-on oversight, collaborative task-solving, and full user takeover. Leveraging these insights, we train language models (LMs) to anticipate when users are likely to intervene based on their interaction styles, yielding a 61.4-63.4% improvement in intervention prediction accuracy over base LMs. Finally, we deploy these intervention-aware models in live web navigation agents and evaluate them in a user study, finding a 26.5% increase in user-rated agent usefulness. Together, our results show structured modeling of human intervention leads to more adaptive, collaborative agents.

模拟网络智能体中的人类差异化交互

Modeling Distinct Human Interaction in Web Agents

摘要

Support