为大模型智能体设计动态信息管控框架，解决传统权限机制失效问题。
A Vision for Access Control in LLM-based Agent Systems
- 将权限控制升级为多维上下文感知的信息流治理
- 通过删减、摘要、改写实现信息的自适应响应
- 适合研究可信智能体与安全可控系统的设计者
基于大模型的智能体具有自主性和情境复杂性，传统访问控制机制难以应对。静态的规则系统在可预测环境中有效，却无法处理智能体交互中动态的信息流。本文提出从二元权限控制向更复杂的信息化治理范式转变，核心挑战不是是否授权，而是如何管理信息流动。为此提出智能体访问控制（AAC）框架，包含两个核心模块：(1) 多维度上下文评估，综合身份、关系、场景与规范；(2) 自适应响应生成，超越简单的允许/拒绝，通过信息删减、摘要与改写实现控制。该愿景由专用的访问控制推理引擎驱动，旨在弥合人类级语境判断与可扩展人工智能安全之间的差距，为可信智能体设计提供新的研究视角。
原文摘要 · Abstract (English)
The autonomy and contextual complexity of LLM-based agents render traditional access control (AC) mechanisms insufficient. Static, rule-based systems designed for predictable environments are fundamentally ill-equipped to manage the dynamic information flows inherent in agentic interactions. This position paper argues for a paradigm shift from binary access control to a more sophisticated model of information governance, positing that the core challenge is not merely about permission, but about governing the flow of information. We introduce Agent Access Control (AAC), a novel framework that reframes AC as a dynamic, context-aware process of information flow governance. AAC operates on two core modules: (1) multi-dimensional contextual evaluation, which assesses not just identity but also relationships, scenarios, and norms; and (2) adaptive response formulation, which moves beyond simple allow/deny decisions to shape information through redaction, summarization, and paraphrasing. This vision, powered by a dedicated AC reasoning engine, aims to bridge the gap between human-like nuanced judgment and scalable Al safety, proposing a new conceptual lens for future research in trustworthy agent design.
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。