用机器学习预测用户对AI代理的权限许可，提升自动化控制能力。
Towards Automating Data Access Permissions in AI Agents
- 基于用户研究构建预测模型，分析沟通语境与个人偏好对授权的影响。
- 模型整体准确率达85.1%，高置信度预测达94.4%。
- 仅需少量训练样本即可显著提升性能，适合部署在实际AI代理系统中。
随着AI代理试图自主代表用户行动，透明度与控制权问题日益突出。我们认为基于权限的访问控制对于赋予用户有效控制至关重要，但传统权限模型难以适应自动化代理执行模式。为此，我们提出面向AI代理的自动化权限管理方案。核心思路是通过用户研究识别影响用户权限决策的因素，并将这些因素编码为基于机器学习的权限管理助手，以预测用户未来决策。研究发现，用户的权限决策受沟通上下文影响，但个体偏好在特定上下文中保持稳定，且与其他参与者趋于一致。基于此，我们构建了权限预测模型，整体准确率达到85.1%，高置信度预测可达94.4%。即使不使用权限历史记录，模型仍可达到66.9%的准确率；仅增加1-4个训练样本，准确率即可提升10.8%。
原文摘要 · Abstract (English)
As AI agents attempt to autonomously act on users' behalf, they raise transparency and control issues. We argue that permission-based access control is indispensable in providing meaningful control to the users, but conventional permission models are inadequate for the automated agentic execution paradigm. We therefore propose automated permission management for AI agents. Our key idea is to conduct a user study to identify the factors influencing users' permission decisions and to encode these factors into an ML-based permission management assistant capable of predicting users' future decisions. We find that participants' permission decisions are influenced by communication context but importantly individual preferences tend to remain consistent within contexts, and align with those of other participants. Leveraging these insights, we develop a permission prediction model achieving 85.1% accuracy overall and 94.4% for high-confidence predictions. We find that even without using permission history, our model achieves an accuracy of 66.9%, and a slight increase of training samples (i.e., 1-4) can substantially increase the accuracy by 10.8%.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。